README.md

Conferences

• CVPR 2025 (Jun, decisions late Feb)
• NAACL 2025 (May, decisions late Jan)
• ICLR 2025 (May, decisions mid Jan)
• TheWebConf 2025 (May, decisions late Jan)
• WSDM 2025 (Mar, decisions late Oct)
• AAAI 2025 (Mar, decisions early Dec)
• NeurIPS 2024 (Dec, decisions late Sep)
• ICDM 2024 (Dec, decisions early Sep)

-------------------------------------------------------------------

LoG 2024 (Nov)

• Revisiting Graph Homophily Measures
• Decomposing force fields as flows on graphs reconstructed from stochastic trajectories
• What Do GNNs Actually Learn? Towards Understanding their Representations
• Ising on the Graph: Task-specific Graph Subsampling via the Ising Model
• Reinforcement Learning Discovers Efficient Decentralized Graph Path Search Strategies
• Cayley Graph Propagation
• Simple GNNs with Low Rank Non-parametric Aggregators
• Edge-Splitting MLP: Node Classification on Homophilic and Heterophilic Graphs without Message Passing
• TRIX: A More Expressive Model for Zero-shot Domain Transfer in Knowledge Graphs
• Asymptotic generalization error of a single-layer graph convolutional network

more

• Preventing Representational Rank Collapse in MPNNs by Splitting the Computational Graph
• Effectiveness of SDP rounding using Hopfield Networks
• xAI-Drop: Don't use what you cannot explain
• Understanding Feature/Structure Interplay in Graph Neural Networks
• Knowledge Graph Preference Contrastive Learning for Recommendation
• DF-GNN: Dynamic Fusion Framework for Attention Graph Neural Networks on GPUs
• GraTeD-MLP: Efficient Node Classification via Graph Transformer Distillation to MLP
• A Neuro-Symbolic Framework for Answering Graph Pattern Queries in Knowledge Graphs
• Optimal performance of Graph Convolutional Networks on the Contextual Stochastic Block Model
• Leveraging Temporal Graph Networks Using Module Decoupling
• Do We Really Need Complicated Graph Learning Models? -- A Simple but Effective Baseline
• A Pure Transformer Pretraining Framework on Text-attributed Graphs
• Hyperbolic Kernel Convolution: A Generic Framework
• Faster Optimization on Sparse Graphs via Neural Reparametrization
• NP-NDS: A Nature-Powered Nonlinear Dynamical System for Power Grid Forecasting
• UTG: Towards a Unified View of Snapshot and Event Based Models for Temporal Graphs
• Flexible Diffusion Scopes with Parameterized Laplacian for Heterophilic Graph Learning
• Towards a GNN Framework for Combinatorial Optimization Problems
• Oversquashing in Hypergraph Neural Networks
• Smoothed Graph Contrastive Learning via Seamless Proximity Integration
• Stochastic Experience-Replay for Graph Continual Learning
• Enhancing Topological Dependencies in Spatio-Temporal Graphs with Cycle Message Passing Blocks
• Matrix Completion with Hypergraphs: Sharp Thresholds and Efficient Algorithms
• Do Neural Scaling Laws Exist on Graph Self-Supervised Learning?
• Sub-graph Based Diffusion Model for Link Prediction
• Multi-Scale High-Resolution Logarithmic Grapher Module for Efficient Vision GNNs
• CrysAtom: Distributed Representation of Atoms for Crystal Property Prediction
• Scalable and Efficient Temporal Graph Representation Learning via Forward Recent Sampling
• A Transferable Graph Autoencoder Framework for Network Alignment
• Motif-aware Attribute Masking for Molecular Graph Pre-training
• On the Expressivity of Persistent Homology in Graph Learning
• Data Augmentation for Supervised Graph Outlier Detection via Latent Diffusion Models
• Neural Scaling Laws on Graphs
• CliquePH: Higher-Order Information for Graph Neural Networks through Persistent Homology on Clique Graphs
• Dynamic Representations of Global Crises: A Temporal Knowledge Graph For Conflicts, Trade and Value Networks

-------------------------------------------------------------------

EMNLP 2024 (Nov)

• Integrating Structural Semantic Knowledge for Enhanced Information Extraction Pre-training
• Message Passing on Semantic-Anchor-Graphs for Fine-grained Emotion Representation Learning and Classification
• Crafting Personalized Agents through Retrieval-Augmented Generation on Editable Memory Graphs
• Incomplete Utterance Rewriting with Editing Operation Guidance and Utterance Augmentation
• CSSL: Contrastive Self-Supervised Learning for Dependency Parsing on Relatively Free Word Ordered and Morphologically Rich Low Resource Languages
• Leveraging Context-Aware Prompting for Commit Message Generation
• Bridging Local Details and Global Context in Text-Attributed Graphs
• The Emergence of Compositional Languages in Multi-entity Referential Games: from Image to Graph Representations
• CoverICL: Selective Annotation for In-Context Learning via Active Graph Coverage
• Inference Helps PLMs' Conceptual Understanding: Improving the Abstract Inference Ability with Hierarchical Conceptual Entailment Graphs

more

• A New Pipeline for Knowledge Graph Reasoning Enhanced by Large Language Models Without Fine-Tuning
• Discovering Knowledge-Critical Subnetworks in Pretrained Language Models
• Extract, Define, Canonicalize: An LLM-based Framework for Knowledge Graph Construction
• TKGT: Redefinition and A New Way of Text-to-Table Tasks Based on Real World Demands and Knowledge Graphs Augmented LLMs
• Towards Cross-Cultural Machine Translation with Retrieval-Augmented Generation from Multilingual Knowledge Graphs
• Generative Subgraph Retrieval for Knowledge Graph--Grounded Dialog Generation
• Context-Aware Adapter Tuning for Few-Shot Relation Learning in Knowledge Graphs
• MP2D: An Automated Topic Shift Dialogue Generation Framework Leveraging Knowledge Graphs
• Knowledge Graph Enhanced Large Language Model Editing
• Improving Knowledge Graph Completion with Structure-Aware Supervised Contrastive Learning
• MoCoKGC: Momentum Contrast Entity Encoding for Knowledge Graph Completion
• Joint Pre-Encoding Representation and Structure Embedding for Efficient and Low-Resource Knowledge Graph Completion
• ATAP: Automatic Template-Augmented Commonsense Knowledge Graph Completion via Pre-Trained Language Models
• Multi-Granularity History and Entity Similarity Learning for Temporal Knowledge Graph Reasoning
• TimeR$^4$ : Time-aware Retrieval-Augmented Large Language Models for Temporal Knowledge Graph Question Answering
• CoTKR: Chain-of-Thought Enhanced Knowledge Rewriting for Complex Knowledge Graph Question Answering
• Right for Right Reasons: Large Language Models for Verifiable Commonsense Knowledge Graph Question Answering
• Generate-on-Graph: Treat LLM as both Agent and KG for Incomplete Knowledge Graph Question Answering
• MAR: Matching-Augmented Reasoning for Enhancing Visual-based Entity Question Answering
• Hierarchical Deconstruction of LLM Reasoning: A Graph-Based Framework for Analyzing Knowledge Utilization
• Evidence-Focused Fact Summarization for Knowledge-Augmented Zero-Shot Question Answering
• Towards Faithful Knowledge Graph Explanation Through Deep Alignment in Commonsense Question Answering
• StorySparkQA: Expert-Annotated QA Pairs with Real-World Knowledge for Children's Story-Based Learning
• XplainLLM: A Knowledge-Augmented Dataset for Reliable Grounded Explanations in LLMs
• Structure Guided Prompt: Instructing Large Language Model in Multi-Step Reasoning by Exploring Graph Structure of the Text
• Do LLMs suffer from Multi-Party Hangover? A Diagnostic Approach to Addressee Recognition and Response Selection in Conversations
• Enhancing High-order Interaction Awareness in LLM-based Recommender Model
• Can Large Language Models Enhance Predictions of Disease Progression? Investigating Through Disease Network Link Prediction
• Predicate Debiasing in Vision-Language Models Integration for Scene Graph Generation Enhancement
• An Empirical Analysis on Spatial Reasoning Capabilities of Large Multimodal Models
• On Fake News Detection with LLM Enhanced Semantics Mining
• Unleashing the Power of Emojis in Texts via Self-supervised Graph Pre-Training
• DKEC: Domain Knowledge Enhanced Multi-Label Classification for Diagnosis Prediction
• Mitigating Matthew Effect: Multi-Hypergraph Boosted Multi-Interest Self-Supervised Learning for Conversational Recommendation
• DGLF: A Dual Graph-based Learning Framework for Multi-modal Sarcasm Detection
• LLMs Are Prone to Fallacies in Causal Inference
• CELLO: Causal Evaluation of Large Vision-Language Models

-------------------------------------------------------------------

ECCV 2024 (Oct)

• The All-Seeing Project V2: Towards General Relation Comprehension of the Open World
• HandDAGT: A Denoising Adaptive Graph Transformer for 3D Hand Pose Estimation
• OpenPSG: Open-Set Panoptic Scene Graph Generation via Large Multimodal Models
• Synchronous Diffusion for Unsupervised Smooth Non-rigid 3D Shape Matching
• Equi-GSPR: Equivariant SE(3) Graph Network Model for Sparse Point Cloud Registration
• Graph Neural Network Causal Explanation via Neural Causal Models
• Confidence Self-calibration for Multi-label Class-Incremental Learning
• Upper-Body Hierarchical Graph for Skeleton Based Emotion Recognition in Assistive Driving
• Skeleton-Based Group Activity Recognition via Spatial-Temporal Panoramic Graph
• CoMusion: Towards Consistent Stochastic Human Motion Prediction via Motion Diffusion

more

• GTP-4o: Modality-Prompted Heterogeneous Graph Learning for Omni-Modal Biomedical Representation
• SceneGraphLoc: Cross-Modal Coarse Visual Localization on 3D Scene Graphs
• GKGNet: Group K-Nearest Neighbor Based Graph Convolutional Network for Multi-label Image Recognition
• POET: Prompt Offset Tuning for Continual Human Action Adaptation
• MART: MultiscAle Relational Transformer Networks for Multi-agent Trajectory Prediction
• SLEDGE: Synthesizing Driving Environments with Generative Models and Rule-Based Traffic
• Generalizable Symbolic Optimizer Learning
• Nonverbal Interaction Detection
• Local Action-Guided Motion Diffusion Model for Text-to-Motion Generation
• SAM-Guided Graph Cut for 3D Instance Segmentation
• On the Topology Awareness and Generalization Performance of Graph Neural Networks
• Scene-Graph ViT: End-to-End Open-Vocabulary Visual Relationship Detection
• PairingNet: A Learning-Based Pair-Searching and -Matching Network for Image Fragments
• SLAck: Semantic, Location, and Appearance Aware Open-Vocabulary Tracking
• Structured-NeRF: Hierarchical Scene Graph with Neural Representation
• Semantic Diversity-Aware Prototype-Based Learning for Unbiased Scene Graph Generation
• SkateFormer: Skeletal-Temporal Transformer for Human Action Recognition
• Towards Scene Graph Anticipation
• Multi-modal Video Dialog State Tracking in the Wild
• SG-NeRF: Neural Surface Reconstruction with Scene Graph Optimization
• ControlLLM: Augment Language Models with Tools by Searching on Graphs
• Occlusion Handling in 3D Human Pose Estimation with Perturbed Positional Encoding
• Lane Graph as Path: Continuity-Preserving Path-Wise Modeling for Online Lane Graph Construction
• A Graph-Based Approach for Category-Agnostic Pose Estimation
• GPSFormer: A Global Perception and Local Structure Fitting-Based Transformer for Point Cloud Understanding
• ``Where am I?'' Scene Retrieval with Language
• Generating 3D House Wireframes with Semantics
• GRACE: Graph-Based Contextual Debiasing for Fair Visual Question Answering
• TreeSBA: Tree-Transformer for Self-supervised Sequential Brick Assembly
• Heterogeneous Graph Learning for Scene Graph Prediction in 3D Point Clouds
• SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understanding
• Visual Relationship Transformation
• SNP: Structured Neuron-Level Pruning to Preserve Attention Scores
• Fine-Grained Scene Graph Generation via Sample-Level Bias Prediction
• EchoScene: Indoor Scene Generation via Information Echo Over Scene Graph Diffusion
• AnimateMe: 4D Facial Expressions via Diffusion Models
• KeypointDETR: An End-to-End 3D Keypoint Detector
• Causal Subgraphs and Information Bottlenecks: Redefining OOD Robustness in Graph Neural Networks
• Masked Video and Body-Worn IMU Autoencoder for Egocentric Action Recognition
• SPAMming Labels: Efficient Annotations for the Trackers of Tomorrow
• NAMER: Non-autoregressive Modeling for Handwritten Mathematical Expression Recognition
• Contextual Correspondence Matters: Bidirectional Graph Matching for Video Summarization
• SENC: Handling Self-collision in Neural Cloth Simulation
• Learning to Distinguish Samples for Generalized Category Discovery
• Multi-Granularity Sparse Relationship Matrix Prediction Network for End-to-End Scene Graph Generation
• Multiscale Graph Texture Network
• External Knowledge Enhanced 3D Scene Generation from Sketch
• DriveLM: Driving with Graph Visual Question Answering
• MAGR: Manifold-Aligned Graph Regularization for Continual Action Quality Assessment
• Improving Hyperbolic Representations via Gromov-Wasserstein Regularization
• GraphBEV: Towards Robust BEV Feature Alignment for Multi-modal 3D Object Detection
• Continuity Preserving Online CenterLine Graph Learning
• COHO: Context-Sensitive City-Scale Hierarchical Urban Layout Generation
• Enhanced Motion Forecasting with Visual Relation Reasoning
• Frontier-Enhanced Topological Memory with Improved Exploration Awareness for Embodied Visual Navigation
• RICA\^2\: Rubric-Informed, Calibrated Assessment of Actions
• SparseRadNet: Sparse Perception Neural Network on Subsampled Radar Data
• VSViG: Real-Time Video-Based Seizure Detection via Skeleton-Based Spatiotemporal ViG
• Expanding Scene Graph Boundaries: Fully Open-Vocabulary Scene Graph Generation via Visual-Concept Alignment and Retention
• SAGS: Structure-Aware 3D Gaussian Splatting
• A Fair Ranking and New Model for Panoptic Scene Graph Generation
• HiFi-Score: Fine-Grained Image Description Evaluation with Hierarchical Parsing Graphs
• PRET: Planning with Directed Fidelity Trajectory for Vision and Language Navigation
• Mew: Multiplexed Immunofluorescence Image Analysis Through an Efficient Multiplex Network
• Hetecooper: Feature Collaboration Graph for Heterogeneous Collaborative Perception

-------------------------------------------------------------------

KDD 2024 (Aug)

• DFGNN: Dual-frequency Graph Neural Network for Sign-aware Feedback
• All in One and One for All: A Simple yet Effective Method towards Cross-domain Graph Pretraining
• AGS-GNN: Attribute-guided Sampling for Graph Neural Networks
• A Deep Prediction Framework for Multi-Source Information via Heterogeneous GNN
• Causal Subgraph Learning for Generalizable Inductive Relation Prediction
• Hypformer: Exploring Efficient Transformer Fully in Hyperbolic Space
• Irregular Traffic Time Series Forecasting Based on Asynchronous Spatio-Temporal Graph Convolutional Networks
• ORCDF: An Oversmoothing-Resistant Cognitive Diagnosis Framework for Student Learning in Online Education Systems
• TSC: A Simple Two-Sided Constraint against Over-Smoothing
• Reserving-Masking-Reconstruction Model for Self-Supervised Heterogeneous Graph Representation

more

• Embedding Two-View Knowledge Graphs with Class Inheritance and Structural Similarity
• Enhancing Contrastive Learning on Graphs with Node Similarity
• Efficient Topology-aware Data Augmentation for High-Degree Graph Neural Networks
• RIGL: A Unified Reciprocal Approach for Tracing the Independent and Group Learning Processes
• PolygonGNN: Representation Learning for Polygonal Geometries with Heterogeneous Visibility Graph
• GinAR: An End-To-End Multivariate Time Series Forecasting Model Suitable for Variable Missing
• An Efficient Subgraph GNN with Provable Substructure Counting Power
• HiFGL: A Hierarchical Framework for Cross-silo Cross-device Federated Graph Learning
• The Heterophilic Snowflake Hypothesis: Training and Empowering GNNs for Heterophilic Graphs
• Motif-Consistent Counterfactuals with Adversarial Refinement for Graph-level Anomaly Detection
• RoutePlacer: An End-to-End Routability-Aware Placer with Graph Neural Network
• Scalable Multitask Learning Using Gradient-based Estimation of Task Affinity
• HiGPT: Heterogeneous Graph Language Model
• Unsupervised Heterogeneous Graph Rewriting Attack via Node Clustering
• GeoMix: Towards Geometry-Aware Data Augmentation
• Rethinking Order Dispatching in Online Ride-Hailing Platforms
• Topology-aware Embedding Memory for Continual Learning on Expanding Networks
• PolyFormer: Scalable Node-wise Filters via Polynomial Graph Transformer
• Repeat-Aware Neighbor Sampling for Dynamic Graph Learning
• Unveiling Global Interactive Patterns across Graphs: Towards Interpretable Graph Neural Networks
• Optimizing OOD Detection in Molecular Graphs: A Novel Approach with Diffusion Models
• Pre-Training Identification of Graph Winning Tickets in Adaptive Spatial-Temporal Graph Neural Networks
• Heuristic Learning with Graph Neural Networks: A Unified Framework for Link Prediction
• DPHGNN: A Dual Perspective Hypergraph Neural Networks
• Global Human-guided Counterfactual Explanations for Molecular Properties via Reinforcement Learning
• Propagation Structure-Aware Graph Transformer for Robust and Interpretable Fake News Detection
• Graph Bottlenecked Social Recommendation
• Influence Maximization via Graph Neural Bandits
• Consistency and Discrepancy-Based Contrastive Tripartite Graph Learning for Recommendations
• GPFedRec: Graph-Guided Personalization for Federated Recommendation
• DyGKT: Dynamic Graph Learning for Knowledge Tracing
• MSPipe: Efficient Temporal GNN Training via Staleness-Aware Pipeline
• Retrieval-Augmented Hypergraph for Multimodal Social Media Popularity Prediction
• An Energy-centric Framework for Category-free Out-of-distribution Node Detection in Graphs
• The Snowflake Hypothesis: Training and Powering GNN with One Node One Receptive Field
• Effective Clustering on Large Attributed Bipartite Graphs
• SimDiff: Simple Denoising Probabilistic Latent Diffusion Model for Data Augmentation on Multi-modal Knowledge Graph
• Rethinking Graph Backdoor Attacks: A Distribution-Preserving Perspective
• Unifying Evolution, Explanation, and Discernment: A Generative Approach for Dynamic Graph Counterfactuals
• Reimagining Graph Classification from a Prototype View with Optimal Transport: Algorithm and Theorem
• Efficient and Effective Implicit Dynamic Graph Neural Network
• Logical Reasoning with Relation Network for Inductive Knowledge Graph Completion
• Latent Diffusion-based Data Augmentation for Continuous-Time Dynamic Graph Model
• Self-Supervised Learning for Graph Dataset Condensation
• A Learned Generalized Geodesic Distance Function-Based Approach for Node Feature Augmentation on Graphs
• Dynamic Neural Dowker Network: Approximating Persistent Homology in Dynamic Directed Graphs
• Conditional Logical Message Passing Transformer for Complex Query Answering
• MemMap: An Adaptive and Latent Memory Structure for Dynamic Graph Learning
• Balanced Confidence Calibration for Graph Neural Networks
• ZeroG: Investigating Cross-dataset Zero-shot Transferability in Graphs
• Bridging and Compressing Feature and Semantic Spaces for Robust Graph Neural Networks: An Information Theory Perspective
• Towards Lightweight Graph Neural Network Search with Curriculum Graph Sparsification
• LPFormer: An Adaptive Graph Transformer for Link Prediction
• GraphWiz: An Instruction-Following Language Model for Graph Computational Problems
• Unsupervised Generative Feature Transformation via Graph Contrastive Pre-training and Multi-objective Fine-tuning
• Graph Mamba: Towards Learning on Graphs with State Space Models
• Unsupervised Alignment of Hypergraphs with Different Scales
• Killing Two Birds with One Stone: Cross-modal Reinforced Prompting for Graph and Language Tasks
• Customizing Graph Neural Network for CAD Assembly Recommendation
• AsyncET: Asynchronous Representation Learning for Knowledge Graph Entity Typing
• Graph Condensation for Open-World Graph Learning
• Capturing Homogeneous Influence among Students: Hypergraph Cognitive Diagnosis for Intelligent Education Systems
• Mastering Long-Tail Complexity on Graphs: Characterization, Learning, and Generalization
• SEBot: Structural Entropy Guided Multi-View Contrastive learning for Social Bot Detection
• Towards Adaptive Neighborhood for Advancing Temporal Interaction Graph Modeling
• Certified Robustness on Visual Graph Matching via Searching Optimal Smoothing Range
• AdaGMLP: AdaBoosting GNN-to-MLP Knowledge Distillation
• Warming Up Cold-Start CTR Prediction by Learning Item-Specific Feature Interactions
• STONE: A Spatio-temporal OOD Learning Framework Kills Both Spatial and Temporal Shifts
• Graph Cross Supervised Learning via Generalized Knowledge
• Cross-Context Backdoor Attacks against Graph Prompt Learning
• Toward Structure Fairness in Dynamic Graph Embedding: A Trend-aware Dual Debiasing Approach
• Privacy-Preserved Neural Graph Databases
• IDEA: A Flexible Framework of Certified Unlearning for Graph Neural Networks
• Revisiting Modularity Maximization for Graph Clustering: A Contrastive Learning Perspective
• Resurrecting Label Propagation for Graphs with Heterophily and Label Noise
• Advancing Molecule Invariant Representation via Privileged Substructure Identification
• Divide and Denoise: Empowering Simple Models for Robust Semi-Supervised Node Classification against Label Noise
• Graph Data Condensation via Self-expressive Graph Structure Reconstruction
• Rethinking Fair Graph Neural Networks from Re-balancing
• Graph Anomaly Detection with Few Labels: A Data-Centric Approach
• Representation Learning of Temporal Graphs with Structural Roles
• One Fits All: Learning Fair Graph Neural Networks for Various Sensitive Attributes
• Optimizing Long-tailed Link Prediction in Graph Neural Networks through Structure Representation Enhancement
• Path-based Explanation for Knowledge Graph Completion
• FUGNN: Harmonizing Fairness and Utility in Graph Neural Networks
• Federated Graph Learning with Structure Proxy Alignment
• Learning Attributed Graphlets: Predictive Graph Mining by Graphlets with Trainable Attribute
• When Box Meets Graph Neural Network in Tag-aware Recommendation
• How Powerful is Graph Filtering for Recommendation
• Topology-monitorable Contrastive Learning on Dynamic Graphs
• Towards Robust Recommendation via Decision Boundary-aware Graph Contrastive Learning
• Co-Neighbor Encoding Schema: A Light-cost Structure Encoding Method for Dynamic Link Prediction
• Leveraging Pedagogical Theories to Understand Student Learning Process with Graph-based Reasonable Knowledge Tracing
• QGRL: Quaternion Graph Representation Learning for Heterogeneous Feature Data Clustering
• NeuroCut: A Neural Approach for Robust Graph Partitioning
• Self-Supervised Denoising through Independent Cascade Graph Augmentation for Robust Social Recommendation
• Effective Edge-wise Representation Learning in Edge-Attributed Bipartite Graphs
• Unveiling Privacy Vulnerabilities: Investigating the Role of Structure in Graph Data
• Multi-source Unsupervised Domain Adaptation on Graphs with Transferability Modeling
• Self-Explainable Temporal Graph Networks based on Graph Information Bottleneck
• GAugLLM: Improving Graph Contrastive Learning for Text-Attributed Graphs with Large Language Models
• Can Modifying Data Address Graph Domain Adaptation?
• LLM4DyG: Can Large Language Models Solve Spatial-Temporal Problems on Dynamic Graphs?
• Unifying Graph Convolution and Contrastive Learning in Collaborative Filtering
• Conformalized Link Prediction on Graph Neural Networks
• Flexible Graph Neural Diffusion with Latent Class Representation Learning
• SLADE: Detecting Dynamic Anomalies in Edge Streams without Labels via Self-Supervised Learning
• Attacking Graph Neural Networks with Bit Flips: Weisfeiler and Leman Go Indifferent
• Investigating Out-of-Distribution Generalization of GNNs: An Architecture Perspective
• Pre-Training and Prompting for Few-Shot Node Classification on Text-Attributed Graphs
• A Novel Prompt Tuning for Graph Transformers: Tailoring Prompts to Graph Topologies
• Relaxing Continuous Constraints of Equivariant Graph Neural Networks for Broad Physical Dynamics Learning
• Pre-train and Refine: Towards Higher Efficiency in K-Agnostic Community Detection without Quality Degradation
• DiffusionE: Reasoning on Knowledge Graphs via Diffusion-based Graph Neural Networks
• DIVE: Subgraph Disagreement for Graph Out-of-Distribution Generalization

-------------------------------------------------------------------

ACL 2024 (Aug)

• Advancement in Graph Understanding: A Multimodal Benchmark and Fine-Tuning of Vision-Language Models
• Revisiting Structured Sentiment Analysis as Latent Dependency Graph Parsing
• Unlocking the Power of Large Language Models for Entity Alignment
• POMP: Probability-driven Meta-graph Prompter for LLMs in Low-resource Unsupervised Neural Machine Translation
• S2GSL: Incorporating Segment to Syntactic Enhanced Graph Structure Learning for Aspect-based Sentiment Analysis
• Beyond Scaling: Predicting Patent Approval with Domain-specific Fine-grained Claim Dependency Graph
• MIDGARD: Self-Consistency Using Minimum Description Length for Structured Commonsense Reasoning
• MindMap: Knowledge Graph Prompting Sparks Graph of Thoughts in Large Language Models
• Event-Radar: Event-driven Multi-View Learning for Multimodal Fake News Detection
• LogogramNLP: Comparing Visual and Textual Representations of Ancient Logographic Writing Systems for NLP

more

• Enhancing Large Language Models in Coding Through Multi-Perspective Self-Consistency
• Fine-Grained Modeling of Narrative Context: A Coherence Perspective via Retrospective Questions
• InstructProtein: Aligning Human and Protein Language via Knowledge Instruction
• HyCoRec: Hypergraph-Enhanced Multi-Preference Learning for Alleviating Matthew Effect in Conversational Recommendation
• ABEX: Data Augmentation for Low-Resource NLU via Expanding Abstract Descriptions
• HOLMES: Hyper-Relational Knowledge Graphs for Multi-hop Question Answering using LLMs
• Exploiting Intrinsic Multilateral Logical Rules for Weakly Supervised Natural Language Video Localization
• Modality-Aware Integration with Large Language Models for Knowledge-Based Visual Question Answering
• Advancing Abductive Reasoning in Knowledge Graphs through Complex Logical Hypothesis Generation
• Graph Language Models
• Hyper-CL: Conditioning Sentence Representations with Hypernetworks
• ANALOGYKB: Unlocking Analogical Reasoning of Language Models with A Million-scale Knowledge Base
• A Unified Temporal Knowledge Graph Reasoning Model Towards Interpolation and Extrapolation
• Evaluating Very Long-Term Conversational Memory of LLM Agents
• Limits of Theory of Mind Modelling in Dialogue-Based Collaborative Plan Acquisition
• Progressively Modality Freezing for Multi-Modal Entity Alignment
• SymKGQA: Few-Shot Knowledge Graph Question Answering via Symbolic Program Generation and Execution
• Multimodal Reasoning with Multimodal Knowledge Graph
• Confidence is not Timeless: Modeling Temporal Validity for Rule-based Temporal Knowledge Graph Forecasting
• Identifying while Learning for Document Event Causality Identification
• PRP-Graph: Pairwise Ranking Prompting to LLMs with Graph Aggregation for Effective Text Re-ranking
• QueryAgent: A Reliable and Efficient Reasoning Framework with Environmental Feedback based Self-Correction
• Large Language Models Can Learn Temporal Reasoning
• Threads of Subtlety: Detecting Machine-Generated Texts Through Discourse Motifs
• SAC-KG: Exploiting Large Language Models as Skilled Automatic Constructors for Domain Knowledge Graph
• REANO: Optimising Retrieval-Augmented Reader Models through Knowledge Graph Generation
• Hypergraph based Understanding for Document Semantic Entity Recognition
• PITA: Prompting Task Interaction for Argumentation Mining
• DynaSemble: Dynamic Ensembling of Textual and Structure-Based Models for Knowledge Graph Completion

-------------------------------------------------------------------

IJCAI 2024 (Aug)

• VSGT: Variational Spatial and Gaussian Temporal Graph Models for EEG-based Emotion Recognition
• CONC: Complex-noise-resistant Open-set Node Classification with Adaptive Noise Detection
• An Efficient Prototype-Based Clustering Approach for Edge Pruning in Graph Neural Networks to Battle Over-Smoothing
• Contrastive and View-Interaction Structure Learning for Multi-view Clustering
• A Logic for Reasoning about Aggregate-Combine Graph Neural Networks
• Dual Contrastive Graph-Level Clustering with Multiple Cluster Perspectives Alignment
• Attention Based Document-level Relation Extraction with None Class Ranking Loss
• Graph Attention Network with High-Order Neighbor Information Propagation for Social Recommendation
• A Context-Enhanced Framework for Sequential Graph Reasoning
• Learning Multi-Granularity and Adaptive Representation for Knowledge Graph Reasoning

more

• LLM-based Multi-Level Knowledge Generation for Few-shot Knowledge Graph Completion
• Gradformer: Graph Transformer with Exponential Decay
• LG-GNN: Local-Global Adaptive Graph Neural Network for Modeling Both Homophily and Heterophily
• Optimal Graph Learning and Nuclear Norm Maximization for Deep Cross-Domain Robust Label Propagation
• Multiplex Graph Representation Learning via Bi-level Optimization
• History Repeats Itself: A Baseline for Temporal Knowledge Graph Forecasting
• Temporal Graph ODEs for Irregularly-Sampled Time Series
• Contrastive General Graph Matching with Adaptive Augmentation Sampling
• SAEIR: Sequentially Accumulated Entropy Intrinsic Reward for Cooperative Multi-Agent Reinforcement Learning with Sparse Reward
• Fast and Continual Knowledge Graph Embedding via Incremental LoRA
• Rank and Align: Towards Effective Source-free Graph Domain Adaptation
• Anomaly Subgraph Detection through High-Order Sampling Contrastive Learning
• Zero-shot Learning for Preclinical Drug Screening
• Temporal Inductive Logic Reasoning over Hypergraphs
• Toward a Manifold-Preserving Temporal Graph Network in Hyperbolic Space
• Graph Collaborative Expert Finding with Contrastive Learning
• Joint Domain Adaptive Graph Convolutional Network
• KDDC: Knowledge-Driven Disentangled Causal Metric Learning for Pre-Travel Out-of-Town Recommendation
• FedTAD: Topology-aware Data-free Knowledge Distillation for Subgraph Federated Learning
• Explore Internal and External Similarity for Single Image Deraining with Graph Neural Networks
• A Graph-based Representation Framework for Trajectory Recovery via Spatiotemporal Interval-Informed Seq2Seq
• A Multi-Valued Decision Diagram-Based Approach to Constrained Optimal Path Problems over Directed Acyclic Graphs
• Domain-Hierarchy Adaptation via Chain of Iterative Reasoning for Few-shot Hierarchical Text Classification
• Joint Multimodal Aspect Sentiment Analysis with Aspect Enhancement and Syntactic Adaptive Learning
• LSPAN: Spectrally Localized Augmentation for Graph Consistency Learning
• Multi-Relational Graph Attention Network for Social Relationship Inference from Human Mobility Data
• MFTraj: Map-Free, Behavior-Driven Trajectory Prediction for Autonomous Driving
• Pre-DyGAE: Pre-training Enhanced Dynamic Graph Autoencoder for Occupational Skill Demand Forecasting
• MMGNN: A Molecular Merged Graph Neural Network for Explainable Solvation Free Energy Prediction
• Subgraph Pooling: Tackling Negative Transfer on Graphs
• KG-CoT: Chain-of-Thought Prompting of Large Language Models over Knowledge Graphs for Knowledge-Aware Question Answering
• Make Graph Neural Networks Great Again: A Generic Integration Paradigm of Topology-Free Patterns for Traffic Speed Prediction
• Dynamicity-aware Social Bot Detection with Dynamic Graph Transformers
• AnchorGT: Efficient and Flexible Attention Architecture for Scalable Graph Transformers
• Where to Mask: Structure-Guided Masking for Graph Masked Autoencoders
• Unified View Imputation and Feature Selection Learning for Incomplete Multi-view Data
• Multi-Granularity Graph-Convolution-Based Method for Weakly Supervised Person Search
• WeatherGNN: Exploiting Meteo- and Spatial-Dependencies for Local Numerical Weather Prediction Bias-Correction
• Group-Aware Coordination Graph for Multi-Agent Reinforcement Learning
• Graph Contrastive Learning with Reinforcement Augmentation
• Exploring the Role of Node Diversity in Directed Graph Representation Learning
• Robust Heterophilic Graph Learning against Label Noise for Anomaly Detection
• Generalized Taxonomy-Guided Graph Neural Networks
• Continual Multimodal Knowledge Graph Construction
• Joint Source Localization in Different Platforms via Implicit Propagation Characteristics of Similar Topics
• SaSDim:Self-Adaptive Noise Scaling Diffusion Model for Spatial Time Series Imputation
• Dynamic Weighted Graph Fusion for Deep Multi-View Clustering
• Towards Geometric Normalization Techniques in SE(3) Equivariant Graph Neural Networks for Physical Dynamics Simulations
• Finding Increasingly Large Extremal Graphs with AlphaZero and Tabu Search
• LG-FGAD: An Effective Federated Graph Anomaly Detection Framework
• Kernel Readout for Graph Neural Networks
• Temporal Knowledge Graph Extrapolation via Causal Subhistory Identification
• CPa-WAC: Constellation Partitioning-based Scalable Weighted Aggregation Composition for Knowledge Graph Embedding
• Integrating Vision-Language Semantic Graphs in Multi-View Clustering
• Cross-View Contrastive Fusion for Enhanced Molecular Property Prediction
• Expressiveness is Effectiveness: Self-supervised Fashion-aware CLIP for Video-to-Shop Retrieval
• DGR: A General Graph Desmoothing Framework for Recommendation via Global and Local Perspectives
• Efficient Tuning and Inference for Large Language Models on Textual Graphs
• Continual Multi-View Clustering with Consistent Anchor Guidance
• Rethinking the Effectiveness of Graph Classification Datasets in Benchmarks for Assessing GNNs
• Hypergraph Self-supervised Learning with Sampling-efficient Signals
• Self-Promoted Clustering-based Contrastive Learning for Brain Networks Pretraining
• CAP: A Context-Aware Neural Predictor for NAS
• Self-Supervised Learning for Enhancing Spatial Awareness in Free-Hand Sketches
• Heterogeneous Graph Transformer with Poly-Tokenization
• Negative Prompt Driven Complementary Parallel Representation for Open-World 3D Object Retrieval
• Make Bricks with a Little Straw: Large-Scale Spatio-Temporal Graph Learning with Restricted GPU-Memory Capacity
• Deep Hierarchical Graph Alignment Kernels
• A General Black-box Adversarial Attack on Graph-based Fake News Detectors
• Unsupervised Deep Graph Structure and Embedding Learning
• DGCD: An Adaptive Denoising GNN for Group-level Cognitive Diagnosis
• Contrastive Learning Drug Response Models from Natural Language Supervision
• Heterogeneous Causal Metapath Graph Neural Network for Gene-Microbe-Disease Association Prediction
• EPIC: Graph Augmentation with Edit Path Interpolation via Learnable Cost
• Predictive Modeling with Temporal Graphical Representation on Electronic Health Records
• HeterGCL: Graph Contrastive Learning Framework on Heterophilic Graph
• Capturing Knowledge Graphs and Rules with Octagon Embeddings
• SVD-AE: Simple Autoencoders for Collaborative Filtering
• A Deep Probabilistic Spatiotemporal Framework for Dynamic Graph Representation Learning with Application to Brain Disorder Identification
• R2V-MIF: Rule-to-Vector Contrastive Learning and Multi-channel Information Fusion for Therapy Recommendation
• An Image-enhanced Molecular Graph Representation Learning Framework
• Hierarchical Reinforcement Learning on Multi-Channel Hypergraph Neural Network for Course Recommendation
• Reinforcement Nash Equilibrium Solver
• FairGT: A Fairness-aware Graph Transformer
• Enhancing Multimodal Knowledge Graph Representation Learning through Triple Contrastive Learning
• PACIA: Parameter-Efficient Adapter for Few-Shot Molecular Property Prediction
• A Semi-supervised Molecular Learning Framework for Activity Cliff Estimation

-------------------------------------------------------------------

ICML 2024 (Jul)

• Less is More: on the Over-Globalizing Problem in Graph Transformers
• LSEnet: Lorentz Structural Entropy Neural Network for Deep Graph Clustering
• EquiPocket: an E(3)-Equivariant Geometric Graph Neural Network for Ligand Binding Site Prediction
• GPTSwarm: Language Agents as Optimizable Graphs
• Multi-Track Message Passing: Tackling Oversmoothing and Oversquashing in Graph Learning via Preventing Heterophily Mixing
• Position: Graph Foundation Models Are Already Here
• Pairwise Alignment Improves Graph Domain Adaptation
• QBMK: Quantum-based Matching Kernels for Un-attributed Graphs
• Feature Distribution on Graph Topology Mediates the Effect of Graph Convolution: Homophily Perspective
• Neural Tangent Kernels Motivate Cross-Covariance Graphs in Neural Networks

more

• Knowledge Graphs Can be Learned with Just Intersection Features
• Delaunay Graph: Addressing Over-Squashing and Over-Smoothing Using Delaunay Triangulation
• Generating In-Distribution Proxy Graphs for Explaining Graph Neural Networks
• Graph Mixup on Approximate Gromov-Wasserstein Geodesics
• Enhancing Size Generalization in Graph Neural Networks through Disentangled Representation Learning
• How Graph Neural Networks Learn: Lessons from Training Dynamics
• Graph Automorphism Group Equivariant Neural Networks
• Hypergraph-enhanced Dual Semi-supervised Graph Classification
• Neurodegenerative Brain Network Classification via Adaptive Diffusion with Temporal Regularization
• Disentangled Graph Self-supervised Learning for Out-of-Distribution Generalization
• Graph Neural Networks with a Distribution of Parametrized Graphs
• Graph Distillation with Eigenbasis Matching
• On the Role of Edge Dependency in Graph Generative Models
• Finite Volume Features, Global Geometry Representations, and Residual Training for Deep Learning-based CFD Simulation
• Proteus: Exploring Protein Structure Generation for Enhanced Designability and Efficiency
• SiT: Symmetry-invariant Transformers for Generalisation in Reinforcement Learning
• Subgraphormer: Unifying Subgraph GNNs and Graph Transformers via Graph Products
• UniCorn: A Unified Contrastive Learning Approach for Multi-view Molecular Representation Learning
• Mitigating Label Noise on Graphs via Topological Sample Selection
• Explaining Graph Neural Networks via Structure-aware Interaction Index
• Weisfeiler Leman for Euclidean Equivariant Machine Learning
• Relational Learning in Pre-Trained Models: A Theory from Hypergraph Recovery Perspective
• Unsupervised Episode Generation for Graph Meta-learning
• Modelling Microbial Communities with Graph Neural Networks
• PGODE: Towards High-quality System Dynamics Modeling
• CKGConv: General Graph Convolution with Continuous Kernels
• Graph Adversarial Diffusion Convolution
• Recurrent Distance Filtering for Graph Representation Learning
• The Expressive Power of Path-Based Graph Neural Networks
• Bounded and Uniform Energy-based Out-of-distribution Detection for Graphs
• Hyperbolic Geometric Latent Diffusion Model for Graph Generation
• Open Ad Hoc Teamwork with Cooperative Game Theory
• Predicting and Interpreting Energy Barriers of Metallic Glasses with Graph Neural Networks
• Graph-enhanced Large Language Models in Asynchronous Plan Reasoning
• Long Range Propagation on Continuous-Time Dynamic Graphs
• Interpreting Equivariant Representations
• On Which Nodes Does GCN Fail? Enhancing GCN From the Node Perspective
• Graph Generation with Diffusion Mixture
• Expressivity and Generalization: Fragment-Biases for Molecular GNNs
• On dimensionality of feature vectors in MPNNs
• Differentiability and Optimization of Multiparameter Persistent Homology
• Subhomogeneous Deep Equilibrium Models
• Embodied CoT Distillation From LLM To Off-the-shelf Agents
• Disentangled Continual Graph Neural Architecture Search with Invariant Modular Supernet
• Class-Imbalanced Graph Learning without Class Rebalancing
• REST: Efficient and Accelerated EEG Seizure Analysis through Residual State Updates
• Effective Federated Graph Matching
• EvoluNet: Advancing Dynamic Non-IID Transfer Learning on Graphs
• An Empirical Study of Realized GNN Expressiveness
• HAMLET: Graph Transformer Neural Operator for Partial Differential Equations
• Towards General Algorithm Discovery for Combinatorial Optimization: Learning Symbolic Branching Policy from Bipartite Graph
• PANDA: Expanded Width-Aware Message Passing Beyond Rewiring
• Graph Geometry-Preserving Autoencoders
• On the Generalization of Equivariant Graph Neural Networks
• LLaGA: Large Language and Graph Assistant
• Simulation of Graph Algorithms with Looped Transformers
• On the Expressive Power of Spectral Invariant Graph Neural Networks
• Projecting Molecules into Synthesizable Chemical Spaces
• SLOG: An Inductive Spectral Graph Neural Network Beyond Polynomial Filter
• Collective Certified Robustness against Graph Injection Attacks
• DiffDA: a Diffusion model for weather-scale Data Assimilation
• Neural SPH: Improved Neural Modeling of Lagrangian Fluid Dynamics
• Efficient Contrastive Learning for Fast and Accurate Inference on Graphs
• Triplet Interaction Improves Graph Transformers: Accurate Molecular Graph Learning with Triplet Graph Transformers
• Locality-Sensitive Hashing-Based Efficient Point Transformer with Applications in High-Energy Physics
• Position: Relational Deep Learning - Graph Representation Learning on Relational Databases
• Unsupervised Parameter-free Simplicial Representation Learning with Scattering Transforms
• Context-Guided Diffusion for Out-of-Distribution Molecular and Protein Design
• GNNs Also Deserve Editing, and They Need It More Than Once
• CARTE: Pretraining and Transfer for Tabular Learning
• Federated Self-Explaining GNNs with Anti-shortcut Augmentations
• Exploring Correlations of Self-Supervised Tasks for Graphs
• Sign is Not a Remedy: Multiset-to-Multiset Message Passing for Learning on Heterophilic Graphs
• Graph Neural Networks Use Graphs When They Shouldn’t
• How Universal Polynomial Bases Enhance Spectral Graph Neural Networks: Heterophily, Over-smoothing, and Over-squashing
• Swallowing the Bitter Pill: Simplified Scalable Conformer Generation
• S3GCL: Spectral, Swift, Spatial Graph Contrastive Learning
• Surprisingly Strong Performance Prediction with Neural Graph Features
• Scene Graph Generation Strategy with Co-occurrence Knowledge and Learnable Term Frequency
• From Geometry to Causality- Ricci Curvature and the Reliability of Causal Inference on Networks
• Graph Neural Network Explanations are Fragile
• PDHG-Unrolled Learning-to-Optimize Method for Large-Scale Linear Programming
• HGCN2SP: Hierarchical Graph Convolutional Network for Two-Stage Stochastic Programming
• Automated Loss function Search for Class-imbalanced Node Classification
• Learning Graph Representation via Graph Entropy Maximization
• Exploiting Code Symmetries for Learning Program Semantics
• Graph-based Time Series Clustering for End-to-End Hierarchical Forecasting
• Irregular Multivariate Time Series Forecasting: A Transformable Patching Graph Neural Networks Approach
• Tackling Prevalent Conditions in Unsupervised Combinatorial Optimization: Cardinality, Minimum, Covering, and More
• Video-of-Thought: Step-by-Step Video Reasoning from Perception to Cognition
• Graph As Point Set
• Prometheus: Out-of-distribution Fluid Dynamics Modeling with Disentangled Graph ODE
• Pluvial Flood Emulation with Hydraulics-informed Message Passing
• Equivariant Graph Neural Operator for Modeling 3D Dynamics
• Homomorphism Counts for Graph Neural Networks: All About That Basis
• Networked Inequality: Preferential Attachment Bias in Graph Neural Network Link Prediction
• Beyond the Federation: Topology-aware Federated Learning for Generalization to Unseen Clients
• Topological Neural Networks go Persistent, Equivariant, and Continuous
• Mitigating Oversmoothing Through Reverse Process of GNNs for Heterophilic Graphs
• Unraveling the Impact of Heterophilic Structures on Graph Positive-Unlabeled Learning
• GATE: How to Keep Out Intrusive Neighbors
• VisionGraph: Leveraging Large Multimodal Models for Graph Theory Problems in Visual Context
• Rethinking Independent Cross-Entropy Loss For Graph-Structured Data
• Graph External Attention Enhanced Transformer
• A Graph is Worth K Words: Euclideanizing Graph using Pure Transformer
• Prospector Heads: Generalized Feature Attribution for Large Models & Data
• Generalist Equivariant Transformer Towards 3D Molecular Interaction Learning
• What Improves the Generalization of Graph Transformers? A Theoretical Dive into the Self-attention and Positional Encoding
• Structure-Aware E(3)-Invariant Molecular Conformer Aggregation Networks
• Optimal Exact Recovery in Semi-Supervised Learning: A Study of Spectral Methods and Graph Convolutional Networks
• Diffuse, Sample, Project: Plug-And-Play Controllable Graph Generation
• Unsupervised Representation Learning of Brain Activity via Bridging Voxel Activity and Functional Connectivity
• Weisfeiler-Leman at the margin: When more expressivity matters
• Empowering Graph Invariance Learning with Deep Spurious Infomax
• Cooperative Graph Neural Networks
• How Interpretable Are Interpretable Graph Neural Networks?
• Graph2Tac: Online Representation Learning of Formal Math Concepts
• Verifying message-passing neural networks via topology-based bounds tightening
• Tackling Non-Stationarity in Reinforcement Learning via Causal-Origin Representation
• EiG-Search: Generating Edge-Induced Subgraphs for GNN Explanation in Linear Time
• The Merit of River Network Topology for Neural Flood Forecasting
• OxyGenerator: Reconstructing Global Ocean Deoxygenation Over a Century with Deep Learning
• Subequivariant Reinforcement Learning in 3D Multi-Entity Physical Environments
• Position: Topological Deep Learning is the New Frontier for Relational Learning
• Community-Invariant Graph Contrastive Learning
• Graph Positional and Structural Encoder
• Uncertainty for Active Learning on Graphs
• Graph-based Forecasting with Missing Data through Spatiotemporal Downsampling
• Towards Neural Architecture Search through Hierarchical Generative Modeling
• Privacy Attacks in Decentralized Learning
• Navigating Complexity: Toward Lossless Graph Condensation via Expanding Window Matching
• Two Heads Are Better Than One: Boosting Graph Sparse Training via Semantic and Topological Awareness
• Generalization Error of Graph Neural Networks in the Mean-field Regime
• Improving Equivariant Graph Neural Networks on Large Geometric Graphs via Virtual Nodes Learning
• LaMAGIC: Language-Model-based Topology Generation for Analog Integrated Circuits
• Learning Latent Structures in Network Games via Data-Dependent Gated-Prior Graph Variational Autoencoders
• Comparing Graph Transformers via Positional Encodings
• Aligning Transformers with Weisfeiler-Leman
• CHEMREASONER: Heuristic Search over a Large Language Model’s Knowledge Space using Quantum-Chemical Feedback
• Perfect Alignment May be Poisonous to Graph Contrastive Learning
• Graph Neural PDE Solvers with Conservation and Similarity-Equivariance
• PAC-Bayesian Generalization Bounds for Knowledge Graph Representation Learning
• MAGDi: Structured Distillation of Multi-Agent Interaction Graphs Improves Reasoning in Smaller Language Models
• Position: Future Directions in the Theory of Graph Machine Learning
• Structure Your Data: Towards Semantic Graph Counterfactuals
• Knowledge-aware Reinforced Language Models for Protein Directed Evolution
• MS-TIP: Imputation Aware Pedestrian Trajectory Prediction
• Editing Partially Observable Networks via Graph Diffusion Models
• Predicting Lagrangian Multipliers for Mixed Integer Linear Programs
• Understanding Heterophily for Graph Neural Networks
• UP2ME: Univariate Pre-training to Multivariate Fine-tuning as a General-purpose Framework for Multivariate Time Series Analysis
• Extending Test-Time Augmentation with Metamorphic Relations for Combinatorial Problems
• DUPLEX: Dual GAT for Complex Embedding of Directed Graphs
• CurBench: Curriculum Learning Benchmark
• Graph Neural Stochastic Diffusion for Estimating Uncertainty in Node Classification
• HGAP: Boosting Permutation Invariant and Permutation Equivariant in Multi-Agent Reinforcement Learning via Graph Attention Network
• Translating Subgraphs to Nodes Makes Simple GNNs Strong and Efficient for Subgraph Representation Learning
• Temporal Spiking Neural Networks with Synaptic Delay for Graph Reasoning
• Graph Structure Extrapolation for Out-of-Distribution Generalization
• Graph Out-of-Distribution Detection Goes Neighborhood Shaping
• KnowFormer: Revisiting Transformers for Knowledge Graph Reasoning
• Quantum Positional Encodings for Graph Neural Networks
• From Coarse to Fine: Enable Comprehensive Graph Self-supervised Learning with Multi-granular Semantic Ensemble
• MAGNOLIA: Matching Algorithms via GNNs for Online Value-to-go Approximation
• Encodings for Prediction-based Neural Architecture Search

-------------------------------------------------------------------

CVPR 2024 (Jun)

• MemoNav: Working Memory Model for Visual Navigation
• SG-PGM: Partial Graph Matching Network with Semantic Geometric Fusion for 3D Scene Graph Alignment and Its Downstream Tasks
• Neural Markov Random Field for Stereo Matching
• MeshGPT: Generating Triangle Meshes with Decoder-Only Transformers
• Domain Separation Graph Neural Networks for Saliency Object Ranking
• Constrained Layout Generation with Factor Graphs
• FlowerFormer: Empowering Neural Architecture Encoding using a Flow-aware Graph Transformer
• Advancing Saliency Ranking with Human Fixations: Dataset Models and Benchmarks
• 3D Feature Tracking via Event Camera
• Error Detection in Egocentric Procedural Task Videos

more

• Clustering for Protein Representation Learning
• Person in Place: Generating Associative Skeleton-Guidance Maps for Human-Object Interaction Image Editing
• CAGE: Controllable Articulation GEneration
• From Pixels to Graphs: Open-Vocabulary Scene Graph Generation with Vision-Language Models
• EGTR: Extracting Graph from Transformer for Scene Graph Generation
• HIG: Hierarchical Interlacement Graph Approach to Scene Graph Generation in Video Understanding
• CURSOR: Scalable Mixed-Order Hypergraph Matching with CUR Decomposition
• HyperSDFusion: Bridging Hierarchical Structures in Language and Geometry for Enhanced 3D Text2Shape Generation
• The Audio-Visual Conversational Graph: From an Egocentric-Exocentric Perspective
• Denoising Point Clouds in Latent Space via Graph Convolution and Invertible Neural Network
• Neighbor Relations Matter in Video Scene Detection
• Composing Object Relations and Attributes for Image-Text Matching
• MaskPLAN: Masked Generative Layout Planning from Partial Input
• Tumor Micro-environment Interactions Guided Graph Learning for Survival Analysis of Human Cancers from Whole-slide Pathological Images
• MESA: Matching Everything by Segmenting Anything
• TeMO: Towards Text-Driven 3D Stylization for Multi-Object Meshes
• Molecular Data Programming: Towards Molecule Pseudo-labeling with Systematic Weak Supervision
• Improving Graph Contrastive Learning via Adaptive Positive Sampling
• Category-Level Multi-Part Multi-Joint 3D Shape Assembly
• Compositional Video Understanding with Spatiotemporal Structure-based Transformers
• HiKER-SGG: Hierarchical Knowledge Enhanced Robust Scene Graph Generation
• Leveraging Predicate and Triplet Learning for Scene Graph Generation
• Dynamic Graph Representation with Knowledge-aware Attention for Histopathology Whole Slide Image Analysis
• GraphDreamer: Compositional 3D Scene Synthesis from Scene Graphs
• Adaptive Hyper-graph Aggregation for Modality-Agnostic Federated Learning
• Dysen-VDM: Empowering Dynamics-aware Text-to-Video Diffusion with LLMs
• Relation Rectification in Diffusion Model
• VS: Reconstructing Clothed 3D Human from Single Image via Vertex Shift
• OED: Towards One-stage End-to-End Dynamic Scene Graph Generation
• XFibrosis: Explicit Vessel-Fiber Modeling for Fibrosis Staging from Liver Pathology Images
• Higher-order Relational Reasoning for Pedestrian Trajectory Prediction
• Multi-Level Neural Scene Graphs for Dynamic Urban Environments
• Object Dynamics Modeling with Hierarchical Point Cloud-based Representations
• G-FARS: Gradient-Field-based Auto-Regressive Sampling for 3D Part Grouping
• FC-GNN: Recovering Reliable and Accurate Correspondences from Interferences
• HHMR: Holistic Hand Mesh Recovery by Enhancing the Multimodal Controllability of Graph Diffusion Models
• GLiDR: Topologically Regularized Graph Generative Network for Sparse LiDAR Point Clouds
• Learning Structure-from-Motion with Graph Attention Networks
• Zero-TPrune: Zero-Shot Token Pruning through Leveraging of the Attention Graph in Pre-Trained Transformers
• CLIP-Driven Open-Vocabulary 3D Scene Graph Generation via Cross-Modality Contrastive Learning
• Open3DSG: Open-Vocabulary 3D Scene Graphs from Point Clouds with Queryable Objects and Open-Set Relationships
• BlockGCN: Redefine Topology Awareness for Skeleton-Based Action Recognition
• SignGraph: A Sign Sequence is Worth Graphs of Nodes
• Multi-agent Long-term 3D Human Pose Forecasting via Interaction-aware Trajectory Conditioning
• LiDAR-based Person Re-identification
• Improving Out-of-Distribution Generalization in Graphs via Hierarchical Semantic Environments
• Generating Handwritten Mathematical Expressions From Symbol Graphs: An End-to-End Pipeline
• DGC-GNN: Leveraging Geometry and Color Cues for Visual Descriptor-Free 2D-3D Matching
• Neural Sign Actors: A Diffusion Model for 3D Sign Language Production from Text
• MaskClustering: View Consensus based Mask Graph Clustering for Open-Vocabulary 3D Instance Segmentation
• DSGG: Dense Relation Transformer for an End-to-end Scene Graph Generation
• OmniVec2 - A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning
• LLM4SGG: Large Language Models for Weakly Supervised Scene Graph Generation
• Bezier Everywhere All at Once: Learning Drivable Lanes as Bezier Graphs
• Compositional Chain-of-Thought Prompting for Large Multimodal Models
• Image Processing GNN: Breaking Rigidity in Super-Resolution
• SOK-Bench: A Situated Video Reasoning Benchmark with Aligned Open-World Knowledge
• Semantic-Aware Multi-Label Adversarial Attacks
• Learning for Transductive Threshold Calibration in Open-World Recognition
• GreedyViG: Dynamic Axial Graph Construction for Efficient Vision GNNs
• DiffAssemble: A Unified Graph-Diffusion Model for 2D and 3D Reassembly

-------------------------------------------------------------------

NAACL 2024 (Jun)

• Exploring Key Point Analysis with Pairwise Generation and Graph Partitioning
• Depression Detection in Clinical Interviews with LLM-Empowered Structural Element Graph
• RE2: Region-Aware Relation Extraction from Visually Rich Documents
• Can Knowledge Graphs Reduce Hallucinations in LLMs? : A Survey
• Head-to-Tail: How Knowledgeable are Large Language Models (LLMs)? A.K.A. Will LLMs Replace Knowledge Graphs?
• Does Pre-trained Language Model Actually Infer Unseen Links in Knowledge Graph Completion?
• The Integration of Semantic and Structural Knowledge in Knowledge Graph Entity Typing
• Few-shot Knowledge Graph Relational Reasoning via Subgraph Adaptation
• GINopic: Topic Modeling with Graph Isomorphism Network
• Semi-Structured Chain-of-Thought: Integrating Multiple Sources of Knowledge for Improved Language Model Reasoning

more

• RESPROMPT: Residual Connection Prompting Advances Multi-Step Reasoning in Large Language Models
• COSIGN: Contextual Facts Guided Generation for Knowledge Graph Completion
• Set-Aligning Framework for Auto-Regressive Event Temporal Graph Generation
• Sentence-level Media Bias Analysis with Event Relation Graph
• An Interactive Framework for Profiling News Media Sources
• zrLLM: Zero-Shot Relational Learning on Temporal Knowledge Graphs with Large Language Models
• HTCCN: Temporal Causal Convolutional Networks with Hawkes Process for Extrapolation Reasoning in Temporal Knowledge Graphs
• A Theory Guided Scaffolding Instruction Framework for LLM-Enabled Metaphor Reasoning

-------------------------------------------------------------------

TheWebConf 2024 (May)

• Friend or Foe? Mining Suspicious Behavior via Graph Capsule Infomax Detector against Fraudsters
• Federated Heterogeneous Graph Neural Network for Privacy-preserving Recommendation
• Graph Contrastive Learning via Interventional View Generation
• GraphTranslator: Aligning Graph Model to Large Language Model for Open-ended Tasks
• Heterogeneous Subgraph Transformer for Fake News Detection
• GAMMA: Graph Neural Network-Based Multi-Bottleneck Localization for Microservices Applications
• Diffusion-based Negative Sampling on Graphs for Link Prediction
• Inductive Graph Alignment Prompt: Bridging the Gap between Graph Pre-training and Inductive Fine-tuning From Spectral Perspective
• Adversarial Mask Explainer for Graph Neural Networks
• Exploring Neural Scaling Law and Data Pruning Methods For Node Classification on Large-scale Graphs

more

• Rethinking Node-wise Propagation for Large-scale Graph Learning
• Divide, Conquer, and Coalesce: Meta Parallel Graph Neural Network for IoT Intrusion Detection at Scale
• Graph-Skeleton: ~1% Nodes are Sufficient to Represent Billion-Scale Graph
• EXGC: Bridging Efficiency and Explainability in Graph Condensation
• Fast Graph Condensation with Structure-based Neural Tangent Kernel
• Cross-Space Adaptive Filter: Integrating Graph Topology and Node Attributes for Alleviating the Over-smoothing Problem
• Optimizing Polynomial Graph Filters: A Novel Adaptive Krylov Subspace Approach
• MuGSI: Distilling GNNs with Multi-Granularity Structural Information for Graph Classification
• A Simple but Effective Approach for Unsupervised Few-Shot Graph Classification
• When Imbalance Meets Imbalance: Structure-driven Learning for Imbalanced Graph Classification
• Game-theoretic Counterfactual Explanation for Graph Neural Networks
• GNNShap: Scalable and Accurate GNN Explanation using Shapley Values
• Globally Interpretable Graph Learning via Distribution Matching
• Graph Fairness Learning under Distribution Shifts
• Fair Graph Representation Learning via Sensitive Attribute Disentanglement
• Endowing Pre-trained Graph Models with Provable Fairness
• Collaborate to Adapt: Source-Free Graph Domain Adaptation via Bi-directional Adaptation
• GraphControl: Adding Conditional Control to Universal Graph Pre-trained Models for Graph Domain Transfer Learning
• Unify Graph Learning with Text: Unleashing LLM Potentials for Session Search
• Can GNN be Good Adapter for LLMs?
• MultiGPrompt for Multi-Task Pre-Training and Prompting on Graphs
• HetGPT: Harnessing the Power of Prompt Tuning in Pre-Trained Heterogeneous Graph Neural Networks
• Temporal Conformity-aware Hawkes Graph Network for Recommendations
• Linear-Time Graph Neural Networks for Scalable Recommendations
• Macro Graph Neural Networks for Online Billion-Scale Recommender Systems
• Distributionally Robust Graph-based Recommendation System
• Unleashing the Power of Knowledge Graph for Recommendation via Invariant Learning
• Hierarchical Graph Signal Processing for Collaborative Filtering
• General Debiasing for Graph-based Collaborative Filtering via Adversarial Graph Dropout
• DSLR: Diversity Enhancement and Structure Learning for Rehearsal-based Graph Continual Learning
• Self-Guided Robust Graph Structure Refinement
• GAUSS: GrAph-customized Universal Self-Supervised Learning
• VilLain: Self-Supervised Learning on Homogeneous Hypergraphs without Features via Virtual Label Propagation
• Low Mileage, High Fidelity: Evaluating Hypergraph Expansion Methods by Quantifying the Information Loss
• Detecting Illicit Food Factories from Chemical Declaration Data via Graph-aware Self-supervised Contrastive Anomaly Ranking
• Graph Contrastive Learning with Kernel Dependence Maximization for Social Recommendation
• Towards Expansive and Adaptive Hard Negative Mining: Graph Contrastive Learning via Subspace Preserving
• Disambiguated Node Classification with Graph Neural Networks
• Graph Contrastive Learning Meets Graph Meta Learning: A Unified Method for Few-shot Node Tasks
• High-Frequency-aware Hierarchical Contrastive Selective Coding for Representation Learning on Text Attributed Graphs
• Graph Contrastive Learning with Cohesive Subgraph Awareness
• Graph Contrastive Learning Reimagined: Exploring Universality
• MARIO: Model Agnostic Recipe for Improving OOD Generalization of Graph Contrastive Learning
• Cooperative Classification and Rationalization for Graph Generalization
• Graph Out-of-Distribution Generalization via Causal Intervention
• DPAR: Decoupled Graph Neural Networks with Node-Level Differential Privacy
• GNNFingers: A Fingerprinting Framework for Verifying Ownerships of Graph Neural Networks
• DenseFlow: Spotting Cryptocurrency Money Laundering in Ethereum Transaction Graphs
• Collaborative Metapath Enhanced Corporate Default Risk Assessment on Heterogeneous Graph
• Toward Practical Entity Alignment Method Design: Insights from New Highly Heterogeneous Knowledge Graph Datasets
• Spectral Heterogeneous Graph Convolutions via Positive Noncommutative Polynomials
• Unifying Local and Global Knowledge: Empowering Large Language Models as Political Experts with Knowledge Graphs
• SSTKG: Simple Spatio-Temporal Knowledge Graph for Intepretable and Versatile Dynamic Information Embedding
• Benchmark and Neural Architecture for Conversational Entity Retrieval from a Knowledge Graph
• Query2GMM: Learning Representation with Gaussian Mixture Model for Reasoning over Knowledge Graphs
• Enhancing Complex Question Answering over Knowledge Graphs through Evidence Pattern Retrieval
• Bridging the Space Gap: Unifying Geometry Knowledge Graph Embedding with Optimal Transport
• UniLP: Unified Topology-aware Generative Framework for Link Prediction in Knowledge Graph
• Robust Link Prediction over Noisy Hyper-Relational Knowledge Graphs via Active Learning
• Fact Embedding through Diffusion Model for Knowledge Graph Completion
• GraphLeak: Patient Record Leakage through Gradients with Knowledge Graph
• Hierarchical Position Embedding of Graphs with Landmarks and Clustering for Link Prediction
• Decoupled Variational Graph Autoencoder for Link Prediction
• Masked Graph Autoencoder with Non-discrete Bandwidths
• Semantic Evolvement Enhanced Graph Autoencoder for Rumor Detection
• Dynamic Graph Information Bottleneck
• Memory Disagreement: A Pseudo-Labeling Measure from Training Dynamics for Semi-supervised Graph Learning
• On the Feasibility of Simple Transformer for Dynamic Graph Modeling
• TATKC: A Temporal Graph Neural Network for Fast Approximate Temporal Katz Centrality Ranking
• Graph Anomaly Detection with Bi-level Optimization
• Causal Graph ODE: Continuous Treatment Effect Modeling in Multi-agent Dynamical Systems
• Invariant Graph Learning for Causal Effect Estimation
• Cost-effective Data Labelling for Graph Neural Networks
• SMUG: Sand Mixing for Unobserved Class Detection in Graph Few-Shot Learning
• Identifying VPN Servers through Graph-Represented Behaviors
• Calibrating Graph Neural Networks from a Data-centric Perspective
• Graph Principal Flow Network for Conditional Graph Generation
• A Quasi-Wasserstein Loss for Learning Graph Neural Networks
• ARTEMIS: Detecting Airdrop Hunters in NFT Markets with a Graph Learning System

-------------------------------------------------------------------

ICLR 2024 (May)

• Graph Neural Networks for Learning Equivariant Representations of Neural Networks
• GraphGuard: Provably Robust Graph Classification against Adversarial Attacks
• Consistency Training with Learnable Data Augmentation for Graph Anomaly Detection with Limited Supervision
• PolyGCL: GRAPH CONTRASTIVE LEARNING via Learnable Spectral Polynomial Filters
• Improving Generalization in Equivariant Graph Neural Networks with Physical Inductive Biases
• Online GNN Evaluation Under Test-time Graph Distribution Shifts
• Graph Metanetworks for Processing Diverse Neural Architectures
• Hybrid Directional Graph Neural Network for Molecules
• GTMGC: Using Graph Transformer to Predict Molecule\textquoterights Ground-State Conformation
• Unleashing the Potential of Fractional Calculus in Graph Neural Networks with FROND

more

• One For All: Towards Training One Graph Model For All Classification Tasks
• InstructScene: Instruction-Driven 3D Indoor Scene Synthesis with Semantic Graph Prior
• MMD Graph Kernel: Effective Metric Learning for Graphs via Maximum Mean Discrepancy
• Neural Snowflakes: Universal Latent Graph Inference via Trainable Latent Geometries
• HiGen: Hierarchical Graph Generative Networks
• Scalable Modular Network: A Framework for Adaptive Learning via Agreement Routing
• From Latent Graph to Latent Topology Inference: Differentiable Cell Complex Module
• LogicMP: A Neuro-symbolic Approach for Encoding First-order Logic Constraints
• DREAM: Dual Structured Exploration with Mixup for Open-set Graph Domain Adaption
• Scalable and Effective Implicit Graph Neural Networks on Large Graphs
• CoRe-GD: A Hierarchical Framework for Scalable Graph Visualization with GNNs
• Graph Parsing Networks
• Boosting Graph Anomaly Detection with Adaptive Message Passing
• Long-Short-Range Message-Passing: A Fragmentation-Based Framework to Capture Non-Local Atomistic Interactions
• Locality-Aware Graph Rewiring in GNNs
• Efficient Sharpness-Aware Minimization for Molecular Graph Transformer Models
• Transformers vs. Message Passing GNNs: Distinguished in Uniform
• Learning Adaptive Multiresolution Transforms via Meta-Framelet-based Graph Convolutional Network
• VCR-Graphormer: A Mini-batch Graph Transformer via Virtual Connections
• InterpGNN: Understand and Improve Generalization Ability of Transdutive GNNs through the Lens of Interplay between Train and Test Nodes
• Beyond Weisfeiler-Lehman: A Quantitative Framework for GNN Expressiveness
• Rethinking and Extending the Probabilistic Inference Capacity of GNNs
• Learning From Simplicial Data Based on Random Walks and 1D Convolutions
• G$\textasciicircum2$N$\textasciicircum2$ : Weisfeiler and Lehman go grammatical
• On the Power of the Weisfeiler-Leman Test for Graph Motif Parameters
• Polynormer: Polynomial-Expressive Graph Transformer in Linear Time
• Efficient Subgraph GNNs by Learning Effective Selection Policies
• Effective Structural Encodings via Local Curvature Profiles
• Understanding Expressivity of Neural KG Reasoning from Rule Structure Learning
• Probabilistically Rewired Message-Passing Neural Networks
• Counting Graph Substructures with Graph Neural Networks
• On the Stability of Expressive Positional Encodings for Graph Neural Networks
• Rethinking the Power of Graph Canonization in Graph Representation Learning with Stability
• Entropy Coding of Unordered Data Structures
• GraphChef: Decision-Tree Recipes to Explain Graph Neural Networks
• Learning to solve Class-Constrained Bin Packing Problems via Encoder-Decoder Model
• Graph Lottery Ticket Automated
• GNNBoundary: Towards Explaining Graph Neural Networks through the Lens of Decision Boundaries
• Towards Robust Fidelity for Evaluating Explainability of Graph Neural Networks
• REFACTOR: Learning to Extract Theorems from Proofs
• GOAt: Explaining Graph Neural Networks via Graph Output Attribution
• UNR-Explainer: Counterfactual Explanations for Unsupervised Node Representation Learning Models
• Conformal Inductive Graph Neural Networks
• Mixture of Weak and Strong Experts on Graphs
• Matrix Manifold Neural Networks++
• GnnX-Bench: Unravelling the Utility of Perturbation-based GNN Explainers through In-depth Benchmarking
• Rayleigh Quotient Graph Neural Networks for Graph-level Anomaly Detection
• Deceptive Fairness Attacks on Graphs via Meta Learning
• Aligning Relational Learning with Lipschitz Fairness
• TASK PLANNING FOR VISUAL ROOM REARRANGEMENT UNDER PARTIAL OBSERVABILITY
• Structural Fairness-aware Active Learning for Graph Neural Networks
• Pose Modulated Avatars from Video
• Adversarial Attacks on Fairness of Graph Neural Networks
• Causality-Inspired Spatial-Temporal Explanations for Dynamic Graph Neural Networks
• Biased Temporal Convolution Graph Network for Time Series Forecasting with Missing Values.
• Deep Temporal Graph Clustering
• VBH-GNN: Variational Bayesian Heterogeneous Graph Neural Networks for Cross-subject Emotion Recognition
• Graph Transformers on EHRs: Better Representation Improves Downstream Performance
• Beyond Spatio-Temporal Representations: Evolving Fourier Transform for Temporal Graphs
• A Generative Pre-Training Framework for Spatio-Temporal Graph Transfer Learning
• Temporal Generalization Estimation in Evolving Graphs
• Graphpulse: Topological representations for temporal graph property prediction
• PRES: Toward Scalable Memory-Based Dynamic Graph Neural Networks
• NP-GL: Extending Power of Nature from Binary Problems to Real-World Graph Learning
• TESTAM: A Time-Enhanced Spatio-Temporal Attention Model with Mixture of Experts
• Decoding Natural Images from EEG for Object Recognition
• Graph-based Virtual Sensing from Sparse and Partial Multivariate Observations
• Self-supervised Heterogeneous Graph Learning: a Homogeneity and Heterogeneity Perspective
• HypeBoy: Generative Self-Supervised Representation Learning on Hypergraphs
• $\textbackslashmathbb\D\textasciicircum2$ Pruning: Message Passing for Balancing Diversity & Difficulty in Data Pruning
• Multimodal Patient Representation Learning with Missing Modalities and Labels
• StructComp: Substituting propagation with Structural Compression in Training Graph Contrastive Learning
• A Graph is Worth 1-bit Spikes: When Graph Contrastive Learning Meets Spiking Neural Networks
• Learning Scalar Fields for Molecular Docking with Fast Fourier Transforms
• Graph Generation with $K\textasciicircum2$-trees
• Learning Over Molecular Conformer Ensembles: Datasets and Benchmarks
• Sum-Product-Set Networks: Deep Tractable Models for Tree-Structured Graphs
• Protein-Ligand Interaction Prior for Binding-aware 3D Molecule Diffusion Models
• A Simple and Scalable Representation for Graph Generation
• Stochastic Gradient Descent for Gaussian Processes Done Right
• Towards Foundational Models for Molecular Learning on Large-Scale Multi-Task Datasets
• Removing Biases from Molecular Representations via Information Maximization
• From Molecules to Materials: Pre-training Large Generalizable Models for Atomic Property Prediction
• Navigating the Design Space of Equivariant Diffusion-Based Generative Models for De Novo 3D Molecule Generation
• Learning to design protein-protein interactions with enhanced generalization
• Evaluating Representation Learning on the Protein Structure Universe
• Generative Adversarial Policy Network for Modelling Protein Complexes
• KW-Design: Pushing the Limit of Protein Deign via Knowledge Refinement
• Self-supervised Pocket Pretraining via Protein Fragment-Surroundings Alignment
• De novo Protein Design Using Geometric Vector Field Networks
• Rigid Protein-Protein Docking via Equivariant Elliptic-Paraboloid Interface Prediction
• Hierarchical Data-efficient Representation Learning for Tertiary Structure-based RNA Design
• Crystalformer: Infinitely Connected Attention for Periodic Structure Encoding
• Long-range Neural Atom Learning for Molecular Graphs
• Complete and Efficient Graph Transformers for Crystal Material Property Prediction
• On the hardness of learning under symmetries
• Orbit-Equivariant Graph Neural Networks
• Fast, Expressive $\textbackslashmathrm\SE(n)$ Equivariant Networks through Weight-Sharing in Position-Orientation Space
• A Characterization Theorem for Equivariant Networks with Point-wise Activations
• EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree Representations
• SaNN: Simple Yet Powerful Simplicial-aware Neural Networks
• Equivariant Matrix Function Neural Networks
• Clifford Group Equivariant Simplicial Message Passing Networks
• Rethinking the Benefits of Steerable Features in 3D Equivariant Graph Neural Networks
• Energy-conserving equivariant GNN for elasticity of lattice architected metamaterials
• Bounding the Expected Robustness of Graph Neural Networks Subject to Node Feature Attacks
• Mitigating Severe Robustness Degradation on Graphs
• iGraphMix: Input Graph Mixup Method for Node Classification
• Robust Angular Synchronization via Directed Graph Neural Networks
• Boosting the Adversarial Robustness of Graph Neural Networks: An OOD Perspective
• Rethinking Complex Queries on Knowledge Graphs with Neural Link Predictors
• Towards Foundation Models for Knowledge Graph Reasoning
• GraphCare: Enhancing Healthcare Predictions with Personalized Knowledge Graphs
• MOFDiff: Coarse-grained Diffusion for Metal-Organic Framework Design
• Local Graph Clustering with Noisy Labels
• Hypergraph Dynamic System
• Encoding Unitig-level Assembly Graphs with Heterophilous Constraints for Metagenomic Contigs Binning
• The Optimal Constant Solution: Predictable Extrapolation in Deep Neural Networks
• Amortized Network Intervention to Steer the Excitatory Point Processes
• Space and time continuous physics simulation from partial observations
• Learning 3D Particle-based Simulators from RGB-D Videos
• AirPhyNet: Harnessing Physics-Guided Neural Networks for Air Quality Prediction
• Symmetric Basis Convolutions for Learning Lagrangian Fluid Mechanics
• BroGNet: Momentum-Conserving Graph Neural Stochastic Differential Equation for Learning Brownian Dynamics
• Towards Cross Domain Generalization of Hamiltonian Representation via Meta Learning
• Q-TAPE: A Task-Agnostic Pre-Trained Approach for Quantum Properties Estimation
• Decoupling Weighing and Selecting for Integrating Multiple Graph Pre-training Tasks
• Training Graph Transformers via Curriculum-Enhanced Attention Distillation
• Mirage: Model-agnostic Graph Distillation for Graph Classification
• VQGraph: Rethinking Graph Representation Space for Bridging GNNs and MLPs
• TEDDY: Trimming Edges with Degree-based Graph Diffusion Strategy
• LightHGNN: Distilling Hypergraph Neural Networks into MLPs for 100x Faster Inference
• Label-free Node Classification on Graphs with Large Language Models (LLMs)
• Deep Reinforcement Learning Guided Improvement Heuristic for Job Shop Scheduling
• Learning Multi-Agent Communication from Graph Modeling Perspective
• Towards Imitation Learning to Branch for MIP: A Hybrid Reinforcement Learning based Sample Augmentation Approach
• A Stochastic Centering Framework for Improving Calibration in Graph Neural Networks
• Uncertainty-aware Graph-based Hyperspectral Image Classification
• ETGraph: A Pioneering Dataset Bridging Ethereum and Twitter
• Neural Common Neighbor with Completion for Link Prediction
• NetInfoF Framework: Measuring and Exploiting Network Usable Information
• Revisiting Link Prediction: a data perspective
• A Topological Perspective on Demystifying GNN-Based Link Prediction Performance
• Learning Flexible Body Collision Dynamics with Hierarchical Contact Mesh Transformer
• Better Neural PDE Solvers Through Data-Free Mesh Movers
• BENO: Boundary-embedded Neural Operators for Elliptic PDEs
• Combining Axes Preconditioners through Kronecker Approximation for Deep Learning
• SAFLEX: Self-Adaptive Augmentation via Feature Label Extrapolation
• HoloNets: Spectral Convolutions do extend to Directed Graphs
• PROGRAM: PROtotype GRAph Model based Pseudo-Label Learning for Test-Time Adaptation
• Forward Learning of Graph Neural Networks
• VFLAIR: A Research Library and Benchmark for Vertical Federated Learning
• Tractable Probabilistic Graph Representation Learning with Graph-Induced Sum-Product Networks
• Rethinking Label Poisoning for GNNs: Pitfalls and Attacks
• Simplicial Representation Learning with Neural $k$-Forms
• FedWon: Triumphing Multi-domain Federated Learning Without Normalization
• Variance-enlarged Poisson Learning for Graph-based Semi-Supervised Learning with Extremely Sparse Labeled Data
• NeuroBack: Improving CDCL SAT Solving using Graph Neural Networks
• Partitioning Message Passing for Graph Fraud Detection
• Harnessing Explanations: LLM-to-LM Interpreter for Enhanced Text-Attributed Graph Representation Learning

-------------------------------------------------------------------

WSDM 2024 (Mar)

• LMBot: Distilling Graph Knowledge into Language Model for Graph-less Deployment in Twitter Bot Detection
• Professional Network Matters: Connections Empower Person-Job Fit
• DeSCo: Towards Generalizable and Scalable Deep Subgraph Counting
• PEACE: Prototype lEarning Augmented transferable framework for Cross-domain rEcommendation
• User Behavior Enriched Temporal Knowledge Graphs for Sequential Recommendation
• Incomplete Graph Learning via Attribute-Structure Decoupled Variational Auto-Encoder
• DiffKG: Knowledge Graph Diffusion Model for Recommendation
• Robust Training for Conversational Question Answering Models with Reinforced Reformulation Generation
• MONET: Modality-Embracing Graph Convolutional Network and Target-Aware Attention for Multimedia Recommendation
• C²DR: Robust Cross-Domain Recommendation based on Causal Disentanglement

more

• Text-Video Retrieval via Multi-Modal Hypergraph Networks
• Global Heterogeneous Graph and Target Interest Denoising for Multi-behavior Sequential Recommendation
• Capturing Temporal Node Evolution via Self-supervised Learning: A New Perspective on Dynamic Graph Learning
• Knowledge Graph Context-Enhanced Diversified Recommendation
• Generative Models for Complex Logical Reasoning over Knowledge Graphs
• MADM: A Model-agnostic Denoising Module for Graph-based Social Recommendation
• Source Free Graph Unsupervised Domain Adaptation
• SSLRec: A Self-Supervised Learning Framework for Recommendation
• GAD-NR: Graph Anomaly Detection via Neighborhood Reconstruction
• ProGAP: Progressive Graph Neural Networks with Differential Privacy Guarantees
• Rethinking and Simplifying Bootstrapped Graph Latents
• Efficient, Direct, and Restricted Black-Box Graph Evasion Attacks to Any-Layer Graph Neural Networks via Influence Function
• Distribution Consistency based Self-Training for Graph Neural Networks with Sparse Labels
• Not All Negatives Are Worth Attending to: Meta-Bootstrapping Negative Sampling Framework for Link Prediction
• LLMRec: Large Language Models with Graph Augmentation for Recommendation
• Neural Kalman Filtering for Robust Temporal Recommendation
• Towards Alignment-Uniformity Aware Representation in Graph Contrastive Learning
• Unified Pretraining for Recommendation via Task Hypergraphs
• PhoGAD: Graph-based Anomaly Behavior Detection with Persistent Homology Optimization
• Maximizing Malicious Influence in Node Injection Attack
• Interpretable Imitation Learning with Dynamic Causal Relations
• RDGCN: Reinforced Dependency Graph Convolutional Network for Aspect-based Sentiment Analysis
• CreST: A Credible Spatiotemporal Learning Framework for Uncertainty-aware Traffic Forecasting
• Pitfalls in Link Prediction with Graph Neural Networks: Understanding the Impact of Target-link Inclusion & Better Practices
• The Devil is in the Data: Learning Fair Graph Neural Networks via Partial Knowledge Distillation
• Dance with Labels: Dual-Heterogeneous Label Graph Interaction for Multi-intent Spoken Language Understanding

-------------------------------------------------------------------

AAAI 2024 (Feb)

• SimCalib: Graph Neural Network Calibration Based on Similarity between Nodes
• NodeMixup: Tackling Under-Reaching for Graph Neural Networks
• WaveNet: Tackling Non-stationary Graph Signals via Graph Spectral Wavelets
• Hypergraph-Guided Disentangled Spectrum Transformer Networks for Near-Infrared Facial Expression Recognition
• Graph of Thoughts: Solving Elaborate Problems with Large Language Models
• Towards Effective and General Graph Unlearning via Mutual Evolution
• Cell Graph Transformer for Nuclei Classification
• Deep Contrastive Graph Learning with Clustering-Oriented Guidance
• SpaceGTN: A Time-Agnostic Graph Transformer Network for Handwritten Diagram Recognition and Segmentation
• Provably Powerful Graph Neural Networks for Directed Multigraphs

more

• StockMixer: A Simple Yet Strong MLP-Based Architecture for Stock Price Forecasting
• Enhancing Multi-Scale Diffusion Prediction via Sequential Hypergraphs and Adversarial Learning
• A Graph Dynamics Prior for Relational Inference
• LAFA: Multimodal Knowledge Graph Completion with Link Aware Fusion and Aggregation
• Rethinking Dimensional Rationale in Graph Contrastive Learning from Causal Perspective
• ResMatch: Residual Attention Learning for Feature Matching
• Propagation Tree Is Not Deep: Adaptive Graph Contrastive Learning Approach for Rumor Detection
• Every Node Is Different: Dynamically Fusing Self-Supervised Tasks for Attributed Graph Clustering
• Span Graph Transformer for Document-Level Named Entity Recognition
• Incomplete Contrastive Multi-View Clustering with High-Confidence Guiding
• Coreference Graph Guidance for Mind-Map Generation
• HAGO-Net: Hierarchical Geometric Massage Passing for Molecular Representation Learning
• A Transfer Approach Using Graph Neural Networks in Deep Reinforcement Learning
• Spectral-Based Graph Neural Networks for Complementary Item Recommendation
• SEA-GWNN: Simple and Effective Adaptive Graph Wavelet Neural Network
• Graph-Based Prediction and Planning Policy Network (GP3Net) for Scalable Self-Driving in Dynamic Environments Using Deep Reinforcement Learning
• TREE-G: Decision Trees Contesting Graph Neural Networks
• Weisfeiler and Lehman Go Paths: Learning Topological Features via Path Complexes
• Deep Incomplete Multi-View Learning Network with Insufficient Label Information
• Adaptive Feature Imputation with Latent Graph for Deep Incomplete Multi-View Clustering
• GIN-SD: Source Detection in Graphs with Incomplete Nodes via Positional Encoding and Attentive Fusion
• Anchoring Path for Inductive Relation Prediction in Knowledge Graphs
• Factorized Explainer for Graph Neural Networks
• CI-STHPAN: Pre-trained Attention Network for Stock Selection with Channel-Independent Spatio-Temporal Hypergraph
• Graph Contrastive Invariant Learning from the Causal Perspective
• GLDL: Graph Label Distribution Learning
• MultiSum: A Multi-Facet Approach for Extractive Social Summarization Utilizing Semantic and Sociological Relationships
• A Dynamic GCN with Cross-Representation Distillation for Event-Based Learning
• Protein 3D Graph Structure Learning for Robust Structure-Based Protein Property Prediction
• Graph Neural Networks with Soft Association between Topology and Attribute
• Object Attribute Matters in Visual Question Answering
• High-Order Structure Based Middle-Feature Learning for Visible-Infrared Person Re-identification
• Self-Supervised Multi-Modal Knowledge Graph Contrastive Hashing for Cross-Modal Search
• Spear and Shield: Adversarial Attacks and Defense Methods for Model-Based Link Prediction on Continuous-Time Dynamic Graphs
• GOODAT: Towards Test-Time Graph Out-of-Distribution Detection
• LLMRG: Improving Recommendations through Large Language Model Reasoning Graphs
• FairSIN: Achieving Fairness in Graph Neural Networks through Sensitive Information Neutralization
• Motif-Aware Riemannian Graph Neural Network with Generative-Contrastive Learning
• Graph Invariant Learning with Subgraph Co-mixup for Out-of-Distribution Generalization
• Signed Graph Neural Ordinary Differential Equation for Modeling Continuous-Time Dynamics
• HGPrompt: Bridging Homogeneous and Heterogeneous Graphs for Few-Shot Prompt Learning
• Commonsense for Zero-Shot Natural Language Video Localization
• PC-Conv: Unifying Homophily and Heterophily with Two-Fold Filtering
• Emotion Rendering for Conversational Speech Synthesis with Heterogeneous Graph-Based Context Modeling
• Explainable Origin-Destination Crowd Flow Interpolation via Variational Multi-Modal Recurrent Graph Auto-Encoder
• X-RefSeg3D: Enhancing Referring 3D Instance Segmentation via Structured Cross-Modal Graph Neural Networks
• Learning to Approximate Adaptive Kernel Convolution on Graphs
• SURER: Structure-Adaptive Unified Graph Neural Network for Multi-View Clustering
• Full-Body Motion Reconstruction with Sparse Sensing from Graph Perspective
• Data-Augmented Curriculum Graph Neural Architecture Search under Distribution Shifts
• ECHO-GL: Earnings Calls-Driven Heterogeneous Graph Learning for Stock Movement Prediction
• BOK-VQA: Bilingual outside Knowledge-Based Visual Question Answering via Graph Representation Pretraining
• Transitivity-Preserving Graph Representation Learning for Bridging Local Connectivity and Role-Based Similarity
• Revisiting Graph-Based Fraud Detection in Sight of Heterophily and Spectrum
• DAG-Aware Variational Autoencoder for Social Propagation Graph Generation
• Learning to Pivot as a Smart Expert
• MKG-FENN: A Multimodal Knowledge Graph Fused End-to-End Neural Network for Accurate Drug--Drug Interaction Prediction
• Poincar'e Differential Privacy for Hierarchy-Aware Graph Embedding
• Memory-Efficient Prompt Tuning for Incremental Histopathology Classification
• Learning Efficient and Robust Multi-Agent Communication via Graph Information Bottleneck
• Recurrent Graph Neural Networks and Their Connections to Bisimulation and Logic
• Hierarchical Topology Isomorphism Expertise Embedded Graph Contrastive Learning
• AdapterGNN: Parameter-Efficient Fine-Tuning Improves Generalization in GNNs
• Uni-MIS: United Multiple Intent Spoken Language Understanding via Multi-View Intent-Slot Interaction
• Gramformer: Learning Crowd Counting via Graph-Modulated Transformer
• MINES: Message Intercommunication for Inductive Relation Reasoning over Neighbor-Enhanced Subgraphs
• PreRoutGNN for Timing Prediction with Order Preserving Partition: Global Circuit Pre-training, Local Delay Learning and Attentional Cell Modeling
• A Joint Framework with Heterogeneous-Relation-Aware Graph and Multi-Channel Label Enhancing Strategy for Event Causality Extraction
• Coupling Graph Neural Networks with Fractional Order Continuous Dynamics: A Robustness Study
• Complete Neural Networks for Complete Euclidean Graphs
• Rethinking Causal Relationships Learning in Graph Neural Networks
• Question Calibration and Multi-Hop Modeling for Temporal Question Answering
• TopoGCL: Topological Graph Contrastive Learning
• Towards Dynamic Spatial-Temporal Graph Learning: A Decoupled Perspective
• Value at Adversarial Risk: A Graph Defense Strategy against Cost-Aware Attacks
• Dynamic Reactive Spiking Graph Neural Network
• Neural Reasoning about Agents' Goals, Preferences, and Actions
• Spatio-Temporal Fusion for Human Action Recognition via Joint Trajectory Graph
• Mixed Geometry Message and Trainable Convolutional Attention Network for Knowledge Graph Completion
• DGA-GNN: Dynamic Grouping Aggregation GNN for Fraud Detection
• A Twist for Graph Classification: Optimizing Causal Information Flow in Graph Neural Networks
• Towards the Disappearing Truth: Fine-Grained Joint Causal Influences Learning with Hidden Variable-Driven Causal Hypergraphs in Time Series
• Improved Graph Contrastive Learning for Short Text Classification
• TextGT: A Double-View Graph Transformer on Text for Aspect-Based Sentiment Analysis
• Dynamic Spiking Graph Neural Networks
• GAMC: An Unsupervised Method for Fake News Detection Using Graph Autoencoder with Masking
• Multimodal Graph Neural Architecture Search under Distribution Shifts
• Graph-Aware Contrasting for Multivariate Time-Series Classification
• SNN-PDE: Learning Dynamic PDEs from Data with Simplicial Neural Networks
• Empowering Dual-Level Graph Self-Supervised Pretraining with Motif Discovery
• DiG-In-GNN: Discriminative Feature Guided GNN-Based Fraud Detector against Inconsistencies in Multi-Relation Fraud Graph
• DR-Label: Label Deconstruction and Reconstruction of GNN Models for Catalysis Systems
• ASWT-SGNN: Adaptive Spectral Wavelet Transform-Based Self-Supervised Graph Neural Network
• p-Laplacian Adaptation for Generative Pre-trained Vision-Language Models
• Self-Interpretable Graph Learning with Sufficient and Necessary Explanations
• Towards Inductive Robustness: Distilling and Fostering Wave-Induced Resonance in Transductive GCNs against Graph Adversarial Attacks
• Label Attentive Distillation for GNN-Based Graph Classification
• G-Adapter: Towards Structure-Aware Parameter-Efficient Transfer Learning for Graph Transformer Networks
• Conformal Crystal Graph Transformer with Robust Encoding of Periodic Invariance
• Rethinking Propagation for Unsupervised Graph Domain Adaptation
• Spatio-Temporal Pivotal Graph Neural Networks for Traffic Flow Forecasting
• Structural Entropy Based Graph Structure Learning for Node Classification
• A New Mechanism for Eliminating Implicit Conflict in Graph Contrastive Learning
• Dual-Channel Learning Framework for Drug-Drug Interaction Prediction via Relation-Aware Heterogeneous Graph Transformer
• A Generalized Neural Diffusion Framework on Graphs
• No Prejudice! Fair Federated Graph Neural Networks for Personalized Recommendation
• CUTS+: High-Dimensional Causal Discovery from Irregular Time-Series
• Open-Set Graph Domain Adaptation via Separate Domain Alignment
• SGFormer: Semantic Graph Transformer for Point Cloud-Based 3D Scene Graph Generation
• ModWaveMLP: MLP-Based Mode Decomposition and Wavelet Denoising Model to Defeat Complex Structures in Traffic Forecasting
• R3CD: Scene Graph to Image Generation with Relation-Aware Compositional Contrastive Control Diffusion
• Barely Supervised Learning for Graph-Based Fraud Detection
• DGCLUSTER: A Neural Framework for Attributed Graph Clustering via Modularity Maximization
• DHGCN: Dynamic Hop Graph Convolution Network for Self-Supervised Point Cloud Learning
• Feature Transportation Improves Graph Neural Networks
• Attribute-Missing Graph Clustering Network
• Multi-Scene Generalized Trajectory Global Graph Solver with Composite Nodes for Multiple Object Tracking
• Learning to Reweight for Generalizable Graph Neural Network
• Behavioral Recognition of Skeletal Data Based on Targeted Dual Fusion Strategy
• Prot2Text: Multimodal Protein's Function Generation with GNNs and Transformers
• Continuous-Time Graph Representation with Sequential Survival Process
• Joint Learning Neuronal Skeleton and Brain Circuit Topology with Permutation Invariant Encoders for Neuron Classification
• HONGAT: Graph Attention Networks in the Presence of High-Order Neighbors
• Refining Latent Homophilic Structures over Heterophilic Graphs for Robust Graph Convolution Networks
• Deep Semantic Graph Transformer for Multi-View 3D Human Pose Estimation
• Expressive Multi-Agent Communication via Identity-Aware Learning
• Dependency Structure-Enhanced Graph Attention Networks for Event Detection
• Improving Distinguishability of Class for Graph Neural Networks
• Fine-Grained Multi-View Hand Reconstruction Using Inverse Rendering
• Data Augmented Graph Neural Networks for Personality Detection
• Homophily-Related: Adaptive Hybrid Graph Filter for Multi-View Graph Clustering
• Kumaraswamy Wavelet for Heterophilic Scene Graph Generation
• Deep Structural Knowledge Exploitation and Synergy for Estimating Node Importance Value on Heterogeneous Information Networks
• Hypergraph Joint Representation Learning for Hypervertices and Hyperedges via Cross Expansion
• GCNext: Towards the Unity of Graph Convolutions for Human Motion Prediction
• Spatial-Semantic Collaborative Cropping for User Generated Content
• ReGCL: Rethinking Message Passing in Graph Contrastive Learning
• Graph Neural Prompting with Large Language Models
• MDGNN: Multi-Relational Dynamic Graph Neural Network for Comprehensive and Dynamic Stock Investment Prediction
• Stratified GNN Explanations through Sufficient Expansion
• KG-TREAT: Pre-training for Treatment Effect Estimation by Synergizing Patient Data with Knowledge Graphs
• Robust Node Classification on Graph Data with Graph and Label Noise
• Hierarchical and Incremental Structural Entropy Minimization for Unsupervised Social Event Detection
• You Only Read Once: Constituency-Oriented Relational Graph Convolutional Network for Multi-Aspect Multi-Sentiment Classification
• LGMRec: Local and Global Graph Learning for Multimodal Recommendation
• Hawkes-Enhanced Spatial-Temporal Hypergraph Contrastive Learning Based on Criminal Correlations
• Fine-Tuning Graph Neural Networks by Preserving Graph Generative Patterns
• MGNet: Learning Correspondences via Multiple Graphs
• Measuring Task Similarity and Its Implication in Fine-Tuning Graph Neural Networks
• KGTS: Contrastive Trajectory Similarity Learning over Prompt Knowledge Graph Embedding
• MSGNet: Learning Multi-Scale Inter-series Correlations for Multivariate Time Series Forecasting
• Higher-Order Graph Convolutional Network with Flower-Petals Laplacians on Simplicial Complexes
• Learning Domain-Independent Heuristics for Grounded and Lifted Planning
• Graph Learning in 4D: A Quaternion-Valued Laplacian to Enhance Spectral GCNs
• Graph Context Transformation Learning for Progressive Correspondence Pruning
• Reverse Multi-Choice Dialogue Commonsense Inference with Graph-of-Thought
• Spatial-Temporal Interplay in Human Mobility: A Hierarchical Reinforcement Learning Approach with Hypergraph Representation
• Neural Gaussian Similarity Modeling for Differential Graph Structure Learning
• Towards Fair Graph Federated Learning via Incentive Mechanisms
• Residual Hyperbolic Graph Convolution Networks
• Heterogeneous Graph Reasoning for Fact Checking over Texts and Tables
• A Plug-and-Play Quaternion Message-Passing Module for Molecular Conformation Representation
• Fully-Connected Spatial-Temporal Graph for Multivariate Time-Series Data
• Improving GNN Calibration with Discriminative Ability: Insights and Strategies
• Sterling: Synergistic Representation Learning on Bipartite Graphs
• Multimodal Event Causality Reasoning with Scene Graph Enhanced Interaction Network
• Improving Expressive Power of Spectral Graph Neural Networks with Eigenvalue Correction
• DOGE-Train: Discrete Optimization on GPU with End-to-End Training
• Interpretable3D: An Ad-Hoc Interpretable Classifier for 3D Point Clouds
• Learning to Optimize Permutation Flow Shop Scheduling via Graph-Based Imitation Learning
• Structural Information Enhanced Graph Representation for Link Prediction
• Adaptive Graph Learning for Multimodal Conversational Emotion Detection
• Dynamic Semantic-Based Spatial Graph Convolution Network for Skeleton-Based Human Action Recognition
• Curriculum-Enhanced Residual Soft An-Isotropic Normalization for Over-Smoothness in Deep GNNs
• Rethinking Graph Masked Autoencoders through Alignment and Uniformity
• A Goal Interaction Graph Planning Framework for Conversational Recommendation
• LaneGraph2Seq: Lane Topology Extraction with Language Model via Vertex-Edge Encoding and Connectivity Enhancement
• ROG_PL: Robust Open-Set Graph Learning via Region-Based Prototype Learning
• COMBHelper: A Neural Approach to Reduce Search Space for Graph Combinatorial Problems
• G^2SAM: Graph-Based Global Semantic Awareness Method for Multimodal Sarcasm Detection
• Unsupervised Neighborhood Propagation Kernel Layers for Semi-supervised Node Classification
• Attention-Induced Embedding Imputation for Incomplete Multi-View Partial Multi-Label Classification
• Progressive Distillation Based on Masked Generation Feature Method for Knowledge Graph Completion
• Temporal Graph Contrastive Learning for Sequential Recommendation
• Graph Reasoning Transformers for Knowledge-Aware Question Answering
• Hyperbolic Graph Diffusion Model
• Catalyst for Clustering-Based Unsupervised Object Re-identification: Feature Calibration
• PosDiffNet: Positional Neural Diffusion for Point Cloud Registration in a Large Field of View with Perturbations
• GraFITi: Graphs for Forecasting Irregularly Sampled Time Series
• Patch-Wise Graph Contrastive Learning for Image Translation
• A Variational Autoencoder for Neural Temporal Point Processes with Dynamic Latent Graphs
• An Efficient Subgraph-Inferring Framework for Large-Scale Heterogeneous Graphs
• An Autoregressive Text-to-Graph Framework for Joint Entity and Relation Extraction
• ADA-GAD: Anomaly-Denoised Autoencoders for Graph Anomaly Detection
• KGDM: A Diffusion Model to Capture Multiple Relation Semantics for Knowledge Graph Embedding
• Discrete Cycle-Consistency Based Unsupervised Deep Graph Matching
• Graph Disentangled Contrastive Learning with Personalized Transfer for Cross-Domain Recommendation
• Union Subgraph Neural Networks
• A Cross-View Hierarchical Graph Learning Hypernetwork for Skill Demand-Supply Joint Prediction
• Exploring Large Language Model for Graph Data Understanding in Online Job Recommendations
• Hypergraph Neural Architecture Search
• Federated Graph Learning under Domain Shift with Generalizable Prototypes
• Tail-STEAK: Improve Friend Recommendation for Tail Users via Self-Training Enhanced Knowledge Distillation

-------------------------------------------------------------------

NeurIPS 2023 (Dec)

• Evaluating Post-hoc Explanations for Graph Neural Networks via Robustness Analysis
• Provable Training for Graph Contrastive Learning
• No Change, No Gain: Empowering Graph Neural Networks with Expected Model Change Maximization for Active Learning
• Demystifying Oversmoothing in Attention-Based Graph Neural Networks
• DIFUSCO: Graph-based Diffusion Solvers for Combinatorial Optimization
• Adversarial Robustness in Graph Neural Networks: A Hamiltonian Approach
• Equivariant Neural Operator Learning with Graphon Convolution
• NewtonCotes Graph Neural Networks: On the Time Evolution of Dynamic Systems
• Structure-free Graph Condensation: From Large-scale Graphs to Condensed Graph-free Data
• Uncertainty Quantification over Graph with Conformalized Graph Neural Networks

more

• PRODIGY: Enabling In-context Learning Over Graphs
• Neural Injective Functions for Multisets, Measures and Graphs via a Finite Witness Theorem
• HyTrel: Hypergraph-enhanced Tabular Data Representation Learning
• Let the Flows Tell: Solving Graph Combinatorial Problems with GFlowNets
• Mitigating the Popularity Bias of Graph Collaborative Filtering: A Dimensional Collapse Perspective
• Graph Contrastive Learning with Stable and Scalable Spectral Encoding
• LinGCN: Structural Linearized Graph Convolutional Network for Homomorphically Encrypted Inference
• PERFOGRAPH: A Numerical Aware Program Graph Representation for Performance Optimization and Program Analysis
• Layer-Neighbor Sampling --- Defusing Neighborhood Explosion in GNNs
• Learning Large Graph Property Prediction via Graph Segment Training
• Neural Relation Graph: A Unified Framework for Identifying Label Noise and Outlier Data
• A Computationally Efficient Sparsified Online Newton Method
• PlanE: Representation Learning over Planar Graphs
• Fused Gromov-Wasserstein Graph Mixup for Graph-level Classifications
• LD2: Scalable Heterophilous Graph Neural Network with Decoupled Embeddings
• Energy Transformer
• Efficient Learning of Linear Graph Neural Networks via Node Subsampling
• Fitting trees to $\ell_1$-hyperbolic distances
• Demystifying Structural Disparity in Graph Neural Networks: Can One Size Fit All?
• Predicting Global Label Relationship Matrix for Graph Neural Networks under Heterophily
• Characterizing Graph Datasets for Node Classification: Homophily-Heterophily Dichotomy and Beyond
• From Trainable Negative Depth to Edge Heterophily in Graphs
• When Do Graph Neural Networks Help with Node Classification? Investigating the Homophily Principle on Node Distinguishability
• A Fractional Graph Laplacian Approach to Oversmoothing
• Multi-resolution Spectral Coherence for Graph Generation with Score-based Diffusion
• Tailoring Self-Attention for Graph via Rooted Subtrees
• Re-Think and Re-Design Graph Neural Networks in Spaces of Continuous Graph Diffusion Functionals
• MeGraph: Capturing Long-Range Interactions by Alternating Local and Hierarchical Aggregation on Multi-Scaled Graph Hierarchy
• TopoSRL: Topology preserving self-supervised Simplicial Representation Learning
• Fragment-based Pretraining and Finetuning on Molecular Graphs
• NAR-Former V2: Rethinking Transformer for Universal Neural Network Representation Learning
• SGFormer: Simplifying and Empowering Transformers for Large-Graph Representations
• Transformers over Directed Acyclic Graphs
• Laplacian Canonization: A Minimalist Approach to Sign and Basis Invariant Spectral Embedding
• Geometric Transformer with Interatomic Positional Encoding
• On Separate Normalization in Self-supervised Transformers
• Efficiently incorporating quintuple interactions into geometric deep learning force fields
• On the Ability of Graph Neural Networks to Model Interactions Between Vertices
• Rethinking Tokenizer and Decoder in Masked Graph Modeling for Molecules
• MAG-GNN: Reinforcement Learning Boosted Graph Neural Network
• Diffusion Probabilistic Models for Structured Node Classification
• What functions can Graph Neural Networks compute on random graphs? The role of Positional Encoding
• Fine-grained Expressivity of Graph Neural Networks
• Graph Convolutional Kernel Machine versus Graph Convolutional Networks
• Facilitating Graph Neural Networks with Random Walk on Simplicial Complexes
• Are GATs Out of Balance?
• Affinity-Aware Graph Networks
• Is Distance Matrix Enough for Geometric Deep Learning?
• Expressivity-Preserving GNN Simulation
• Going beyond persistent homology using persistent homology
• Calibrate and Boost Logical Expressiveness of GNN Over Multi-Relational and Temporal Graphs
• Three Iterations of (d 1)-WL Test Distinguish Non Isometric Clouds of d-dimensional Points
• Distance-Restricted Folklore Weisfeiler-Leman GNNs with Provable Cycle Counting Power
• The expressive power of pooling in Graph Neural Networks
• FourierGNN: Rethinking Multivariate Time Series Forecasting from a Pure Graph Perspective
• Approximately Equivariant Graph Networks
• A new perspective on building efficient and expressive 3D equivariant graph neural networks
• Latent Field Discovery in Interacting Dynamical Systems with Neural Fields
• Expressive Sign Equivariant Networks for Spectral Geometric Learning
• Unifying Predictions of Deterministic and Stochastic Physics in Mesh-reduced Space with Sequential Flow Generative Model
• Modeling Dynamics over Meshes with Gauge Equivariant Nonlinear Message Passing
• D4Explainer: In-distribution Explanations of Graph Neural Network via Discrete Denoising Diffusion
• Interpretable Prototype-based Graph Information Bottleneck
• TempME: Towards the Explainability of Temporal Graph Neural Networks via Motif Discovery
• SAME: Uncovering GNN Black Box with Structure-aware Shapley-based Multipiece Explanations
• Interpretable Graph Networks Formulate Universal Algebra Conjectures
• Evaluating the Robustness of Interpretability Methods through Explanation Invariance and Equivariance
• V-InFoR: A Robust Graph Neural Networks Explainer for Structurally Corrupted Graphs
• Fair Graph Distillation
• Optimality of Message-Passing Architectures for Sparse Graphs
• Towards Self-Interpretable Graph-Level Anomaly Detection
• Sheaf Hypergraph Networks
• CAT-Walk: Inductive Hypergraph Learning via Set Walks
• Towards Better Dynamic Graph Learning: New Architecture and Unified Library
• Environment-Aware Dynamic Graph Learning for Out-of-Distribution Generalization
• Spectral Invariant Learning for Dynamic Graphs under Distribution Shifts
• CrossGNN: Confronting Noisy Multivariate Time Series Via Cross Interaction Refinement
• Scale-teaching: Robust Multi-scale Training for Time Series Classification with Noisy Labels
• Frequency-domain MLPs are More Effective Learners in Time Series Forecasting
• Taming Local Effects in Graph-based Spatiotemporal Forecasting
• Recurrent Temporal Revision Graph Networks
• Deciphering Spatio-Temporal Graph Forecasting: A Causal Lens and Treatment
• SpatialRank: Urban Event Ranking with NDCG Optimization on Spatiotemporal Data
• GPT-ST: Generative Pre-Training of Spatio-Temporal Graph Neural Networks
• AMAG: Additive, Multiplicative and Adaptive Graph Neural Network For Forecasting Neuron Activity
• Operator Learning with Neural Fields: Tackling PDEs on General Geometries
• Geometry-Informed Neural Operator for Large-Scale 3D PDEs
• Improving Graph Matching with Positional Reconstruction Encoder-Decoder Network
• LVM-Med: Learning Large-Scale Self-Supervised Vision Models for Medical Imaging via Second-order Graph Matching
• GraphPatcher: Mitigating Degree Bias for Graph Neural Networks via Test-time Augmentation
• Self-supervised Graph Neural Networks via Low-Rank Decomposition
• Unsupervised Graph Neural Architecture Search with Disentangled Self-Supervision
• ESSEN: Improving Evolution State Estimation for Temporal Networks using Von Neumann Entropy
• MuSe-GNN: Learning Unified Gene Representation From Multimodal Biological Graph Data
• GALOPA: Graph Transport Learning with Optimal Plan Alignment
• Improving Self-supervised Molecular Representation Learning using Persistent Homology
• Architecture Matters: Uncovering Implicit Mechanisms in Graph Contrastive Learning
• Understanding Contrastive Learning via Distributionally Robust Optimization
• An Empirical Study Towards Prompt-Tuning for Graph Contrastive Pre-Training in Recommendations
• GeoTMI: Predicting Quantum Chemical Property with Easy-to-Obtain Geometry via Positional Denoising
• GIMLET: A Unified Graph-Text Model for Instruction-Based Molecule Zero-Shot Learning
• Prefix-Tree Decoding for Predicting Mass Spectra from Molecules
• Functional-Group-Based Diffusion for Pocket-Specific Molecule Generation and Elaboration
• Learning to Group Auxiliary Datasets for Molecule
• Accelerating Molecular Graph Neural Networks via Knowledge Distillation
• Transfer learning for atomistic simulations using GNNs and kernel mean embeddings
• Optimizing over trained GNNs via symmetry breaking
• A Hierarchical Training Paradigm for Antibody Structure-sequence Co-design
• Graph Denoising Diffusion for Inverse Protein Folding
• Graph-Structured Gaussian Processes for Transferable Graph Learning
• Multi-task Graph Neural Architecture Search with Task-aware Collaboration and Curriculum
• Better with Less: A Data-Active Perspective on Pre-Training Graph Neural Networks
• Limits, approximation and size transferability for GNNs on sparse graphs via graphops
• Context-guided Embedding Adaptation for Effective Topic Modeling in Low-Resource Regimes
• Joint Learning of Label and Environment Causal Independence for Graph Out-of-Distribution Generalization
• Does Invariant Graph Learning via Environment Augmentation Learn Invariance?
• Improving Compositional Generalization using Iterated Learning and Simplicial Embeddings
• A graphon-signal analysis of graph neural networks
• Unleashing the Power of Graph Data Augmentation on Covariate Distribution Shift
• Rethinking Semi-Supervised Imbalanced Node Classification from Bias-Variance Decomposition
• Adversarial Training for Graph Neural Networks: Pitfalls, Solutions, and New Directions
• Provable Adversarial Robustness for Group Equivariant Tasks: Graphs, Point Clouds, Molecules, and More
• Certifiably Robust Graph Contrastive Learning
• Hierarchical Randomized Smoothing
• Optimal Block-wise Asymmetric Graph Construction for Graph-based Semi-supervised Learning
• Learning Rule-Induced Subgraph Representations for Inductive Relation Prediction
• Differentiable Neuro-Symbolic Reasoning on Large-Scale Knowledge Graphs
• Learning from Both Structural and Textual Knowledge for Inductive Knowledge Graph Completion
• NuTrea: Neural Tree Search for Context-guided Multi-hop KGQA
• WalkLM: A Uniform Language Model Fine-tuning Framework for Attributed Graph Embedding
• GraphAdapter: Tuning Vision-Language Models With Dual Knowledge Graph
• Can Language Models Solve Graph Problems in Natural Language?
• EvoPrompting: Language Models for Code-Level Neural Architecture Search
• Directional diffusion models for graph representation learning
• Data-Centric Learning from Unlabeled Graphs with Diffusion Model
• Act As You Wish: Fine-Grained Control of Motion Diffusion Model with Hierarchical Semantic Graphs
• Diffusion Model for Graph Inverse Problems: Towards Effective Source Localization on Complex Networks
• Circuit as Set of Points
• SyncTREE: Fast Timing Analysis for Integrated Circuit Design through a Physics-informed Tree-based Graph Neural Network
• MMGP: a Mesh Morphing Gaussian Process-based machine learning method for regression of physical problems under nonparametrized geometrical variability
• Learning Efficient Surrogate Dynamic Models with Graph Spline Networks
• Equivariant Spatio-Temporal Attentive Graph Networks to Simulate Physical Dynamics
• Graph Mixture of Experts: Learning on Large-Scale Graphs with Explicit Diversity Modeling
• Universal Prompt Tuning for Graph Neural Networks
• FedGCN: Convergence-Communication Tradeoffs in Federated Training of Graph Convolutional Networks
• Train Once and Explain Everywhere: Pre-training Interpretable Graph Neural Networks
• Suggesting Variable Order for Cylindrical Algebraic Decomposition via Reinforcement Learning
• Swarm Reinforcement Learning for Adaptive Mesh Refinement
• Unsupervised Learning for Solving the Travelling Salesman Problem
• Neural Multi-Objective Combinatorial Optimization with Diversity Enhancement
• GNNEvaluator: Evaluating GNN Performance On Unseen Graphs Without Labels
• Improvements on Uncertainty Quantification for Node Classification via Distance Based Regularization
• Evaluating Robustness and Uncertainty of Graph Models Under Structural Distributional Shifts
• Differentially Private Decoupled Graph Convolutions for Multigranular Topology Protection
• Penguin: Parallel-Packed Homomorphic Encryption for Fast Graph Convolutional Network Inference
• Combating Bilateral Edge Noise for Robust Link Prediction
• A Theory of Link Prediction via Relational Weisfeiler-Leman on Knowledge Graphs
• Cross-links Matter for Link Prediction: Rethinking the Debiased GNN from a Data Perspective
• Deep Insights into Noisy Pseudo Labeling on Graph Data
• Curvature Filtrations for Graph Generative Model Evaluation
• Neural Graph Generation from Graph Statistics
• Graph of Circuits with GNN for Exploring the Optimal Design Space
• Lovász Principle for Unsupervised Graph Representation Learning
• Model-Based Control with Sparse Neural Dynamics
• ARTree: A Deep Autoregressive Model for Phylogenetic Inference
• Towards Label Position Bias in Graph Neural Networks
• Maximum Independent Set: Self-Training through Dynamic Programming
• On Class Distributions Induced by Nearest Neighbor Graphs for Node Classification of Tabular Data
• GraphMP: Graph Neural Network-based Motion Planning with Efficient Graph Search
• What Planning Problems Can A Relational Neural Network Solve?
• Joint Feature and Differentiable $ k $-NN Graph Learning using Dirichlet Energy
• Language Semantic Graph Guided Data-Efficient Learning
• RH-BrainFS: Regional Heterogeneous Multimodal Brain Networks Fusion Strategy
• Generalised f-Mean Aggregation for Graph Neural Networks
• Learning To Dive In Branch And Bound
• Learning Invariant Representations of Graph Neural Networks via Cluster Generalization
• A Neural Collapse Perspective on Feature Evolution in Graph Neural Networks
• A Metadata-Driven Approach to Understand Graph Neural Networks
• Kronecker-Factored Approximate Curvature for Modern Neural Network Architectures
• Zero-One Laws of Graph Neural Networks
• Hyperbolic Graph Neural Networks at Scale: A Meta Learning Approach
• High dimensional, tabular deep learning with an auxiliary knowledge graph
• Reversible and irreversible bracket-based dynamics for deep graph neural networks
• Curriculum Learning for Graph Neural Networks: Which Edges Should We Learn First
• Extending the Design Space of Graph Neural Networks by Rethinking Folklore Weisfeiler-Lehman
• Truncated Affinity Maximization: One-class Homophily Modeling for Graph Anomaly Detection
• CARE: Modeling Interacting Dynamics Under Temporal Environmental Variation
• Simple and Asymmetric Graph Contrastive Learning without Augmentations
• NAP: Neural 3D Articulated Object Prior

-------------------------------------------------------------------

ICDM 2023 (Dec)

• Reinforcement Neighborhood Selection for Unsupervised Graph Anomaly Detection
• Graph Self-Contrast Representation Learning
• FM-IGNN: Interaction Graph Neural Network with Fine-grained Matching for Session-based Recommendation
• Self-supervised Heterogeneous Hypergraph Learning with Context-aware Pooling for Graph-level Classification
• Boosting Urban Prediction via Addressing Spatial-Temporal Distribution Shift
• Enhancing Graph Collaborative Filtering via Neighborhood Structure Embedding
• Federated Learning for Privacy-Preserving Prediction of Occupational Group Mobility Using Multi-Source Mobile Data
• Hypergraph Attribute Attention Network for Community Recommendation
• Interpretable Subgraph Feature Extraction for Hyperlink Prediction
• Discovering Protein Interactions and Repurposing Drugs in SARS-CoV-2 (COVID-19) via Learning on Robust Multipartite Graphs

more

• Auto Graph Filtering for Bundle Recommendation
• GMMDA: Gaussian Mixture Modeling of Graph in Latent Space for Graph Data Augmentation
• MPGraf: a Modular and Pre-trained Graphformer for Learning to Rank at Web-scale
• Efficient and Effective Entity Alignment for Evolving Temporal Knowledge Graphs
• Telecom Fraud Detection Based on Feature Binning and Autoencoder
• IE-Evo: Internal and External Evolution-Enhanced Temporal Knowledge Graph Forecasting
• Hierarchical Graph Contrastive Learning via Debiasing Noise Samples with Adaptive Repelling Ratio
• Graph Sampling based Fairness-aware Recommendation over Sensitive Attribute Removal
• Variational Collective Graph AutoEncoder for Multi-behavior Recommendation
• PKAT: Pre-training in Collaborative Knowledge Graph Attention Network for Recommendation
• Meteorology-Assisted Spatio-Temporal Graph Network for Uncivilized Urban Event Prediction
• Robust Network Alignment with the Combination of Structure and Attribute Embeddings
• MCRec: Multi-channel Gated Gifts Recommendation
• DeepRicci: Self-supervised Graph Structure-Feature Co-Refinement for Alleviating Over-squashing
• Limitations of Perturbation-based Explanation Methods for Temporal Graph Neural Networks
• Mitigating Multisource Biases in Graph Neural Networks via Real Counterfactual Samples
• Collaborative Word-based Pre-trained Item Representation for Transferable Recommendation
• Context Sketching for Memory-efficient Graph Representation Learning
• Infinitely Deep Graph Transformation Networks
• IKGN: Intention-aware Knowledge Graph Network for POI Recommendation
• Toward Interpretable Graph Neural Networks via Concept Matching Model
• Bilateral Sequential Hypergraph Convolution Network for Reciprocal Recommendation
• Equipping Federated Graph Neural Networks with Structure-aware Group Fairness
• Entropy Aware Training for Fast and Accurate Distributed GNN
• Towards Unsupervised Graph Completion Learning on Graphs with Features and Structure Missing
• RDKG: A Reinforcement Learning Framework for Disease Diagnosis on Knowledge Graph
• Multi-Hop Correlation Preserving Hashing for Efficient Hamming Space Retrieval
• Pseudo-Labeling with Graph Active Learning for Few-shot Node Classification
• Decision-focused Graph Neural Networks for Graph Learning and Optimization
• CaT: Balanced Continual Graph Learning with Graph Condensation
• Hypergraph Contrastive Learning for Drug Trafficking Community Detection
• Uncertainty-aware Traffic Prediction under Missing Data
• PatSTEG: Modeling Formation Dynamics of Patent Citation Networks via The Semantic-Topological Evolutionary Graph
• A Graph Convolutional Neural Network for Recommendation Based on Community Detection and Combination of Multiple Heterogeneous Graphs
• Rethinking Temporal Dependencies in Multiple Time Series: A Use Case in Financial Data
• PREM: A Simple Yet Effective Approach for Node-Level Graph Anomaly Detection
• Two-Level Graph Representation Learning with Community-as-a-Node Graphs
• On the Verification of Embeddings with Hybrid Markov Logic
• Early Spatiotemporal Event Prediction via Adaptive Controller and Spatiotemporal Embedding
• MTT-DynGL: Towards Multidimensional Topology-oriented Time-series Dynamic Graphs Learning Model
• Session-based Interactive Recommendation via Deep Reinforcement Learning
• Double Wins: Boosting Accuracy and Efficiency of Graph Neural Networks by Reliable Knowledge Distillation
• Enhancing Personalized Healthcare via Capturing Disease Severity, Interaction, and Progression
• To Predict or to Reject: Causal Effect Estimation with Uncertainty on Networked Data
• Graph Collaborative Optimization for Sequential Recommendation
• Graph Neural Ordinary Differential Equations-based method for Collaborative Filtering
• Graph Reciprocal Neural Networks by Abstracting Node as Attribute
• Graph Open-Set Recognition via Entropy Message Passing
• Homogeneous Entity Context Enhanced Representation Network for Temporal Knowledge Graph Reasoning
• Spatio-Temporal Hypergraph Neural ODE Network for Traffic Forecasting
• Contrastive Learning-based Multi-behavior Recommendation with Semantic Knowledge Enhancement
• Dimensionality and Curvature Selection of Graph Embedding using Decomposed Normalized Maximum Likelihood Code-Length
• Enhancing GNN-based Fraud Detector via Semantic Extraction and Max-Representation-Margin
• Unfairness in Distributed Graph Frameworks
• STSD: Modeling Spatial Temporal Staticity and Dynamicity in Traffic Forecasting

-------------------------------------------------------------------

EMNLP 2023 (Dec)

• Improving Image Captioning via Predicting Structured Concepts
• Promoting Topic Coherence and Inter-Document Consorts in Multi-Document Summarization via Simplicial Complex and Sheaf Graph
• ReasoningLM: Enabling Structural Subgraph Reasoning in Pre-trained Language Models for Question Answering over Knowledge Graph
• MingOfficial: A Ming Official Career Dataset and a Historical Context-Aware Representation Learning Framework
• Sentiment Analysis on Streaming User Reviews via Dual-Channel Dynamic Graph Neural Network
• Joint Entity and Relation Extraction with Span Pruning and Hypergraph Neural Networks
• MADNet: Maximizing Addressee Deduction Expectation for Multi-Party Conversation Generation
• Conversational Semantic Parsing using Dynamic Context Graphs
• Learning Co-Speech Gesture for Multimodal Aphasia Type Detection
• Beyond Detection: A Defend-and-Summarize Strategy for Robust and Interpretable Rumor Analysis on Social Media

more

• Characterizing and Verifying Scientific Claims: Qualitative Causal Structure is All You Need
• Conversation Understanding using Relational Temporal Graph Neural Networks with Auxiliary Cross-Modality Interaction
• Detecting Spoilers in Movie Reviews with External Movie Knowledge and User Networks
• Decoding the Silent Majority: Inducing Belief Augmented Social Graph with Large Language Model for Response Forecasting
• Temporal Knowledge Graph Forecasting Without Knowledge Using In-Context Learning
• Knowledge Graph Compression Enhances Diverse Commonsense Generation
• Standardizing Distress Analysis: Emotion-Driven Distress Identification and Cause Extraction (DICE) in Multimodal Online Posts
• Rumor Detection on Social Media with Crowd Intelligence and ChatGPT-Assisted Networks
• Automatic Debate Evaluation with Argumentation Semantics and Natural Language Argument Graph Networks
• Transfer-Free Data-Efficient Multilingual Slot Labeling
• CoSyn: Detecting Implicit Hate Speech in Online Conversations Using a Context Synergized Hyperbolic Network
• Granularity Matters: Pathological Graph-driven Cross-modal Alignment for Brain CT Report Generation
• Enhancing Structured Evidence Extraction for Fact Verification
• Content- and Topology-Aware Representation Learning for Scientific Multi-Literature
• Enhancing Biomedical Lay Summarisation with External Knowledge Graphs
• A Diffusion Weighted Graph Framework for New Intent Discovery
• Structure-aware Knowledge Graph-to-text Generation with Planning Selection and Similarity Distinction
• STINMatch: Semi-Supervised Semantic-Topological Iteration Network for Financial Risk Detection via News Label Diffusion
• Beyond Shared Vocabulary: Increasing Representational Word Similarities across Languages for Multilingual Machine Translation
• E-CORE: Emotion Correlation Enhanced Empathetic Dialogue Generation
• Multi-view Contrastive Learning for Entity Typing over Knowledge Graphs
• Exploring Discourse Structure in Document-level Machine Translation
• Hi-ArG: Exploring the Integration of Hierarchical Argumentation Graphs in Language Pretraining
• Distance-Based Propagation for Efficient Knowledge Graph Reasoning
• CP-BCS: Binary Code Summarization Guided by Control Flow Graph and Pseudo Code
• Anaphor Assisted Document-Level Relation Extraction
• MolCA: Molecular Graph-Language Modeling with Cross-Modal Projector and Uni-Modal Adapter
• Graph vs. Sequence: An Empirical Study on Knowledge Forms for Knowledge-Grounded Dialogue
• Joyful: Joint Modality Fusion and Graph Contrastive Learning for Multimoda Emotion Recognition
• CoCo: Coherence-Enhanced Machine-Generated Text Detection Under Low Resource With Contrastive Learning

-------------------------------------------------------------------

LOG 2023 (Nov)

• Asynchronous Algorithmic Alignment with Cocycles
• Meta-Path Learning for Multi-relational Graph Neural Networks
• On Performance Discrepancies Across Local Homophily Levels in Graph Neural Networks
• Recursive Algorithmic Reasoning
• Cycle Invariant Positional Encoding for Graph Representation Learning
• MUDiff: Unified Diffusion for Complete Molecule Generation
• HOT: Higher-Order Dynamic Graph Representation Learning with Efficient Transformers
• BeMap: Balanced Message Passing for Fair Graph Neural Network
• Generalized Reasoning with Graph Neural Networks by Relational Bayesian Network Encodings
• Rethinking Higher-order Representation Learning with Graph Neural Networks

more

• Transferable Hypergraph Neural Networks via Spectral Similarity
• Edge Directionality Improves Learning on Heterophilic Graphs
• SURF: A Generalization Benchmark for GNNs Predicting Fluid Dynamics
• Intrinsically Motivated Graph Exploration Using Network Theories of Human Curiosity
• A Simple Latent Variable Model for Graph Learning and Inference
• Rank Collapse Causes Over-Smoothing and Over-Correlation in Graph Neural Networks
• Latent Space Representations of Neural Algorithmic Reasoners
• GwAC: GNNs with Asynchronous Communication
• Inferring dynamic regulatory interaction graphs from time series data with perturbations
• Mitigating Over-smoothing and Over-squashing using Augmentations of Forman-Ricci Curvature
• Will More Expressive Graph Neural Networks do Better on Generative Tasks?
• Multicoated and Folded Graph Neural Networks with Strong Lottery Tickets
• Generative modeling of labeled graphs under data scarcity
• United We Stand, Divided We Fall: Networks to Graph (N2G) Abstraction for Robust Graph Classification under Graph Label Corruption
• GSCAN: Graph Stability Clustering for Applications with Noise using Edge-Aware Excess-of-Mass
• HEAL: Unlocking the Potential of Learning on Hypergraphs Enriched with Attributes and Layers
• PyTorch Geometric Signed Directed: A Software Package on Graph Neural Networks for Signed and Directed Graphs
• EMP: Effective Multidimensional Persistence for Graph Representation Learning
• Three Revisits to Node-Level Graph Anomaly Detection: Outliers, Message Passing and Hyperbolic Neural Networks
• A Latent Diffusion Model for Protein Structure Generation
• Neural Algorithmic Reasoning for Combinatorial Optimisation
• Parallel Algorithms Align with Neural Execution

-------------------------------------------------------------------

ICCV 2023 (Oct)

• Physics-Augmented Autoencoder for 3D Skeleton-Based Gait Recognition
• DCPB: Deformable Convolution Based on the Poincare Ball for Top-view Fisheye Cameras
• Learning Adaptive Neighborhoods for Graph Neural Networks
• PC-Adapter: Topology-Aware Adapter for Efficient Domain Adaption on Point Clouds with Rectified Pseudo-label
• MolGrapher: Graph-based Visual Recognition of Chemical Structures
• CheckerPose: Progressive Dense Keypoint Localization for Object Pose Estimation with Graph Neural Network
• Efficient Deep Space Filling Curve
• End2End Multi-View Feature Matching with Differentiable Pose Optimization
• VQA-GNN: Reasoning with Multimodal Knowledge via Graph Neural Networks for Visual Question Answering
• 3DMOTFormer: Graph Transformer for Online 3D Multi-Object Tracking

more

• HandR2N2: Iterative 3D Hand Pose Estimation Using a Residual Recurrent Neural Network
• Spectral Graphormer: Spectral Graph-Based Transformer for Egocentric Two-Hand Reconstruction using Multi-View Color Images
• Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action Recognition
• Detecting Objects with Context-Likelihood Graphs and Graph Refinement
• SGAligner: 3D Scene Alignment with Scene Graphs
• SkeletonMAE: Graph-based Masked Autoencoder for Skeleton Sequence Pre-training
• Chasing Clouds: Differentiable Volumetric Rasterisation of Point Clouds as a Highly Efficient and Accurate Loss for Large-Scale Deformable 3D Registration
• Visual Traffic Knowledge Graph Generation from Scene Images
• DMNet: Delaunay Meshing Network for 3D Shape Representation
• HM-ViT: Hetero-Modal Vehicle-to-Vehicle Cooperative Perception with Vision Transformer
• CO-PILOT: Dynamic Top-Down Point Cloud with Conditional Neighborhood Aggregation for Multi-Gigapixel Histopathology Image Representation
• Scene Graph Contrastive Learning for Embodied Navigation
• Fg-T2M: Fine-Grained Text-Driven Human Motion Generation via Diffusion Model
• GlueStick: Robust Image Matching by Sticking Points and Lines Together
• Re:PolyWorld - A Graph Neural Network for Polygonal Scene Parsing
• HopFIR: Hop-wise GraphFormer with Intragroup Joint Refinement for 3D Human Pose Estimation
• MAPConNet: Self-supervised 3D Pose Transfer with Mesh and Point Contrastive Learning
• Probabilistic Human Mesh Recovery in 3D Scenes from Egocentric Views
• Open-vocabulary Video Question Answering: A New Benchmark for Evaluating the Generalizability of Video Question Answering Models
• Face Clustering via Graph Convolutional Networks with Confidence Edges
• ReST: A Reconfigurable Spatial-Temporal Graph Model for Multi-Camera Multi-Object Tracking
• GraphEcho: Graph-Driven Unsupervised Domain Adaptation for Echocardiogram Video Segmentation
• Leveraging Spatio-Temporal Dependency for Skeleton-Based Action Recognition
• DDG-Net: Discriminability-Driven Graph Network for Weakly-supervised Temporal Action Localization
• SkeleTR: Towards Skeleton-based Action Recognition in the Wild
• GPGait: Generalized Pose-based Gait Recognition
• Persistent-Transient Duality: A Multi-Mechanism Approach for Modeling Human-Object Interaction
• GlobalMapper: Arbitrary-Shaped Urban Layout Generation
• FSAR: Federated Skeleton-based Action Recognition with Adaptive Topology Structure and Knowledge Distillation
• Boosting Few-shot Action Recognition with Graph-guided Hybrid Matching
• GLA-GCN: Global-local Adaptive Graph Convolutional Network for 3D Human Pose Estimation from Monocular Video
• Video Action Segmentation via Contextually Refined Temporal Keypoints
• WaterMask: Instance Segmentation for Underwater Imagery
• Dynamic Hyperbolic Attention Network for Fine Hand-object Reconstruction
• Reconstructing Groups of People with Hypergraph Relational Reasoning
• Learn TAROT with MENTOR: A Meta-Learned Self-Supervised Approach for Trajectory Prediction
• VertexSerum: Poisoning Graph Neural Networks for Link Inference
• Vision HGNN: An Image is More than a Graph of Nodes
• Improved Knowledge Transfer for Semi-Supervised Domain Adaptation via Trico Training Strategy
• ReactioNet: Learning High-Order Facial Behavior from Universal Stimulus-Reaction by Dyadic Relation Reasoning
• Decoupled Iterative Refinement Framework for Interacting Hands Reconstruction from a Single RGB Image
• Virtual Try-On with Pose-Garment Keypoints Guided Inpainting
• Narrator: Towards Natural Control of Human-Scene Interaction Generation via Relationship Reasoning
• HDG-ODE: A Hierarchical Continuous-Time Model for Human Pose Forecasting
• ShapeScaffolder: Structure-Aware 3D Shape Generation from Text
• RLSAC: Reinforcement Learning Enhanced Sample Consensus for End-to-End Robust Estimation
• CoSign: Exploring Co-occurrence Signals in Skeleton-based Continuous Sign Language Recognition
• CLIP-Cluster: CLIP-Guided Attribute Hallucination for Face Clustering
• SimMatchV2: Semi-Supervised Learning with Graph Consistency
• Normalizing Flows for Human Pose Anomaly Detection

-------------------------------------------------------------------

IJCAI 2023 (Aug)

• Beyond Homophily: Robust Graph Anomaly Detection via Neural Sparsification
• Stability and Generalization of lp-Regularized Stochastic Learning for GCN
• Towards Hierarchical Policy Learning for Conversational Recommendation with Hypergraph-based Reinforcement Learning
• Deep Partial Multi-Label Learning with Graph Disambiguation
• Commonsense Knowledge Enhanced Sentiment Dependency Graph for Sarcasm Detection
• Graph Propagation Transformer for Graph Representation Learning
• G2Pxy: Generative Open-Set Node Classification on Graphs with Proxy Unknowns
• Capturing the Long-Distance Dependency in the Control Flow Graph via Structural-Guided Attention for Bug Localization
• Multi-View Robust Graph Representation Learning for Graph Classification
• Some Might Say All You Need Is Sum

more

• Local and Global: Temporal Question Answering via Information Fusion
• SAD: Semi-Supervised Anomaly Detection on Dynamic Graphs
• Dual Relation Knowledge Distillation for Object Detection
• KDLGT: A Linear Graph Transformer Framework via Kernel Decomposition Approach
• An Effective and Efficient Time-aware Entity Alignment Framework via Two-aspect Three-view Label Propagation
• iRe2f: Rethinking Effective Refinement in Language Structure Prediction via Efficient Iterative Retrospecting and Reasoning
• Hierarchical Transformer for Scalable Graph Learning
• Multi-view Contrastive Learning Hypergraph Neural Network for Drug-Microbe-Disease Association Prediction
• SemiGNN-PPI: Self-Ensembling Multi-Graph Neural Network for Efficient and Generalizable Protein–Protein Interaction Prediction
• Diagram Visual Grounding: Learning to See with Gestalt-Perceptual Attention
• Graph Sampling-based Meta-Learning for Molecular Property Prediction
• LGI-GT: Graph Transformers with Local and Global Operators Interleaving
• Fighting against Organized Fraudsters Using Risk Diffusion-based Parallel Graph Neural Network
• Forecasting Soil Moisture Using Domain Inspired Temporal Graph Convolution Neural Networks To Guide Sustainable Crop Management
• Basket Representation Learning by Hypergraph Convolution on Repeated Items for Next-basket Recommendation
• Continuous-Time Graph Learning for Cascade Popularity Prediction
• Sequential Attention Source Identification Based on Feature Representation
• Deep Hierarchical Communication Graph in Multi-Agent Reinforcement Learning
• Towards an Integrated View of Semantic Annotation for POIs with Spatial and Textual Information
• Multi-level Graph Contrastive Prototypical Clustering
• A Generalized Deep Markov Random Fields Framework for Fake News Detection
• Dynamic Group Link Prediction in Continuous-Time Interaction Network
• CADParser: A Learning Approach of Sequence Modeling for B-Rep CAD
• U-Match: Two-view Correspondence Learning with Hierarchy-aware Local Context Aggregation
• Causal-Based Supervision of Attention in Graph Neural Network: A Better and Simpler Choice towards Powerful Attention
• Doubly Stochastic Graph-based Non-autoregressive Reaction Prediction
• Action Recognition with Multi-stream Motion Modeling and Mutual Information Maximization
• MolHF: A Hierarchical Normalizing Flow for Molecular Graph Generation
• Don't Ignore Alienation and Marginalization: Correlating Fraud Detection
• Globally Consistent Federated Graph Autoencoder for Non-IID Graphs
• CSGCL: Community-Strength-Enhanced Graph Contrastive Learning
• Totally Dynamic Hypergraph Neural Networks
• Not Only Pairwise Relationships: Fine-Grained Relational Modeling for Multivariate Time Series Forecasting
• A Canonicalization-Enhanced Known Fact-Aware Framework For Open Knowledge Graph Link Prediction
• LSGNN: Towards General Graph Neural Network in Node Classification by Local Similarity
• Gapformer: Graph Transformer with Graph Pooling for Node Classification
• Intent-aware Recommendation via Disentangled Graph Contrastive Learning
• Self-supervised Graph Disentangled Networks for Review-based Recommendation
• CONGREGATE: Contrastive Graph Clustering in Curvature Spaces
• Interpret ESG Rating’s Impact on the Industrial Chain Using Graph Neural Networks
• Adaptive Path-Memory Network for Temporal Knowledge Graph Reasoning
• Learning Object Consistency and Interaction in Image Generation from Scene Graphs
• An Ensemble Approach for Automated Theorem Proving Based on Efficient Name Invariant Graph Neural Representations
• Federated Graph Semantic and Structural Learning
• Disentanglement of Latent Representations via Causal Interventions
• Multi-Scale Subgraph Contrastive Learning
• Graph Neural Convection-Diffusion with Heterophily
• KMF: Knowledge-Aware Multi-Faceted Representation Learning for Zero-Shot Node Classification
• PPAT: Progressive Graph Pairwise Attention Network for Event Causality Identification
• Deep Multi-view Subspace Clustering with Anchor Graph
• One Model, Any CSP: Graph Neural Networks as Fast Global Search Heuristics for Constraint Satisfaction
• Musical Voice Separation as Link Prediction: Modeling a Musical Perception Task as a Multi-Trajectory Tracking Problem
• Preventing Attacks in Interbank Credit Rating with Selective-aware Graph Neural Network
• Violin: Virtual Overbridge Linking for Enhancing Semi-supervised Learning on Graphs with Limited Labels
• Generative Flow Networks for Precise Reward-Oriented Active Learning on Graphs
• Semi-supervised Domain Adaptation in Graph Transfer Learning
• FedHGN: A Federated Framework for Heterogeneous Graph Neural Networks
• A Unification Framework for Euclidean and Hyperbolic Graph Neural Networks
• Exploring Effective Inter-Encoder Semantic Interaction for Document-Level Relation Extraction
• Toward Convex Manifolds: A Geometric Perspective for Deep Graph Clustering of Single-cell RNA-seq Data
• Do We Need an Encoder-Decoder to Model Dynamical Systems on Networks?

-------------------------------------------------------------------

KDD 2023 (Aug)

• Maintaining the Status Quo: Capturing Invariant Relations for OOD Spatiotemporal Learning
• MixupExplainer: Generalizing Explanations for Graph Neural Networks with Data Augmentation
• Enhancing Node-Level Adversarial Defenses by Lipschitz Regularization of Graph Neural Networks
• Multi-Grained Multimodal Interaction Network for Entity Linking
• Frigate: Frugal Spatio-temporal Forecasting on Road Networks
• Learning Strong Graph Neural Networks with Weak Information
• GAT-MF: Graph Attention Mean Field for Very Large Scale Multi-Agent Reinforcement Learning
• PERT-GNN: Latency Prediction for Microservice-based Cloud-Native Applications via Graph Neural Networks
• CF-GODE: Continuous-Time Causal Inference for Multi-Agent Dynamical Systems
• Contrastive Cross-scale Graph Knowledge Synergy

more

• Towards Graph-level Anomaly Detection via Deep Evolutionary Mapping
• CARL-G: Clustering-Accelerated Representation Learning on Graphs
• Mitigating Action Hysteresis in Traffic Signal Control with Traffic Predictive Reinforcement Learning
• Incremental Causal Graph Learning for Online Root Cause Analysis
• κHGCN: Tree-likeness Modeling via Continuous and Discrete Curvature Learning
• Graph Contrastive Learning with Generative Adversarial Network
• Empower Post-hoc Graph Explanations with Information Bottleneck: A Pre-training and Fine-tuning Perspective
• Enhancing Graph Representations Learning with Decorrelated Propagation
• Classification of Edge-dependent Labels of Nodes in Hypergraphs
• On Structural Expressive Power of Graph Transformers
• What's Behind the Mask: Understanding Masked Graph Modeling for Graph Autoencoders
• Interpretable Sparsification of Brain Graphs: Better Practices and Effective Designs for Graph Neural Networks
• GraphSHA: Synthesizing Harder Samples for Class-Imbalanced Node Classification
• CFGL-LCR: A Counterfactual Graph Learning Framework for Legal Case Retrieval
• Fairness-Aware Continuous Predictions of Multiple Analytics Targets in Dynamic Networks
• Leveraging Relational Graph Neural Network for Transductive Model Ensemble
• Counterfactual Learning on Heterogeneous Graphs with Greedy Perturbation
• Community-based Dynamic Graph Learning for Popularity Prediction
• Heterformer: Transformer-based Deep Node Representation Learning on Heterogeneous Text-Rich Networks
• QTIAH-GNN: Quantity and Topology Imbalance-aware Heterogeneous Graph Neural Network for Bankruptcy Prediction
• Localised Adaptive Spatial-Temporal Graph Neural Network
• E-commerce Search via Content Collaborative Graph Neural Network
• Less is More: SlimG for Accurate, Robust, and Interpretable Graph Mining
• Multi-Temporal Relationship Inference in Urban Areas
• Hyperbolic Graph Topic Modeling Network with Continuously Updated Topic Tree
• Semi-Supervised Graph Imbalanced Regression
• Knowledge Graph Self-Supervised Rationalization for Recommendation
• Shift-Robust Molecular Relational Learning with Causal Substructure
• Pattern Expansion and Consolidation on Evolving Graphs for Continual Traffic Prediction
• Graph Neural Bandits
• Causal Effect Estimation on Hierarchical Spatial Graph Data
• Automated 3D Pre-Training for Molecular Property Prediction
• PROSE: Graph Structure Learning via Progressive Strategy
• EXTRACT and REFINE: Finding a Support Subgraph Set for Graph Representation
• AdaProp: Learning Adaptive Propagation for Graph Neural Network based Knowledge Graph Reasoning
• Rumor Detection with Diverse Counterfactual Evidence
• Financial Default Prediction via Motif-preserving Graph Neural Network with Curriculum Learning
• Improving Expressivity of GNNs with Subgraph-specific Factor Embedded Normalization
• When to Pre-Train Graph Neural Networks? From Data Generation Perspective!
• Temporal Dynamics-Aware Adversarial Attacks on Discrete-Time Dynamic Graph Models
• Certified Edge Unlearning for Graph Neural Networks
• FLOOD: A Flexible Invariant Learning Framework for Out-of-Distribution Generalization on Graphs
• Dual-view Molecular Pre-training
• FLAMES2Graph: An Interpretable Federated Multivariate Time Series Classification Framework
• MGNN: Graph Neural Networks Inspired by Distance Geometry Problem
• Graph Neural Processes for Spatio-Temporal Extrapolation
• Pyramid Graph Neural Network: A Graph Sampling and Filtering Approach for Multi-scale Disentangled Representations
• DyTed: Disentangled Representation Learning for Discrete-time Dynamic Graph
• A Unified Framework of Graph Information Bottleneck for Robustness and Membership Privacy
• Meta Graph Learning for Long-tail Recommendation
• 3D-IDS: Doubly Disentangled Dynamic Intrusion Detection
• DECOR: Degree-Corrected Social Graph Refinement for Fake News Detection
• GraphGLOW: Universal and Generalizable Structure Learning for Graph Neural Networks
• Task-Equivariant Graph Few-shot Learning
• All in One: Multi-Task Prompting for Graph Neural Networks
• Similarity Preserving Adversarial Graph Contrastive Learning
• Kernel Ridge Regression-Based Graph Dataset Distillation
• Narrow the Input Mismatch in Deep Graph Neural Network Distillation
• B2-Sampling: Fusing Balanced and Biased Sampling for Graph Contrastive Learning
• A Message Passing Neural Network Space for Better Capturing Data-dependent Receptive Fields
• GetPt: Graph-enhanced General Table Pre-training with Alternate Attention Network
• Networked Time Series Imputation via Position-aware Graph Enhanced Variational Autoencoders
• Clenshaw Graph Neural Networks
• Spatial Heterophily Aware Graph Neural Networks
• Multiplex Heterogeneous Graph Neural Network with Behavior Pattern Modeling
• HomoGCL: Rethinking Homophily in Graph Contrastive Learning
• Efficient and Effective Edge-wise Graph Representation Learning
• On Hierarchical Disentanglement of Interactive Behaviors for Multimodal Spatiotemporal Data with Incompleteness
• On Manipulating Signals of User-Item Graph: A Jacobi Polynomial-based Graph Collaborative Filtering
• Improving the Expressiveness of K-hop Message-Passing GNNs by Injecting Contextualized Substructure Information
• Representation Learning on Hyper-Relational and Numeric Knowledge Graphs with Transformers
• Context-aware Event Forecasting via Graph Disentanglement
• Generalizing Graph ODE for Learning Complex System Dynamics across Environments
• Recognizing Unseen Objects via Multimodal Intensive Knowledge Graph Propagation
• Reconstructing Graph Diffusion History from a Single Snapshot
• A Data-centric Framework to Endow Graph Neural Networks with Out-Of-Distribution Detection Ability
• Grace: Graph Self-Distillation and Completion to Mitigate Degree-Related Biases
• Joint Pre-training and Local Re-training: Transferable Representation Learning on Multi-source Knowledge Graphs
• WinGNN: Dynamic Graph Neural Networks with Random Gradient Aggregation Window
• Criteria Tell You More than Ratings: Criteria Preference-Aware Light Graph Convolution for Effective Multi-Criteria Recommendation
• Transferable Graph Structure Learning for Graph-based Traffic Forecasting Across Cities
• Few-shot Low-resource Knowledge Graph Completion with Multi-view Task Representation Generation
• Augmenting Recurrent Graph Neural Networks with a Cache

-------------------------------------------------------------------

ICML 2023 (Jul)

• GRAFENNE: Learning on Graphs with Heterogeneous and Dynamic Feature Sets
• End-to-End Full-Atom Antibody Design
• Revisiting Over-smoothing and Over-squashing Using Ollivier-Ricci Curvature
• A Gromov-Wasserstein Geometric View of Spectrum-Preserving Graph Coarsening
• Dink-Net: Neural Clustering on Large Graphs
• Training Deep Surrogate Models with Large Scale Online Learning
• WL meet VC
• Graph Neural Tangent Kernel: Convergence on Large Graphs
• FAENet: Frame Averaging Equivariant GNN for Materials Modeling
• Learning the Right Layers a Data-Driven Layer-Aggregation Strategy for Semi-Supervised Learning on Multilayer Graphs

more

• Node Embedding from Neural Hamiltonian Orbits in Graph Neural Networks
• Curriculum Co-disentangled Representation Learning across Multiple Environments for Social Recommendation
• Distribution Free Prediction Sets for Node Classification
• Relevant Walk Search for Explaining Graph Neural Networks
• Towards Understanding and Reducing Graph Structural Noise for GNNs
• Contrastive Learning Meets Homophily: Two Birds with One Stone
• Quantifying the Knowledge in GNNs for Reliable Distillation into MLPs
• Neural Status Registers
• What Makes Entities Similar? A Similarity Flooding Perspective for Multi-sourced Knowledge Graph Embeddings
• Demystifying Uneven Vulnerability of Link Stealing Attacks against Graph Neural Networks
• Multi-Layer Neural Networks as Trainable Ladders of Hilbert Spaces
• On the Initialization of Graph Neural Networks
• RSC: Accelerate Graph Neural Networks Training via Randomized Sparse Computations
• Metagenomic Binning using Connectivity-constrained Variational Autoencoders
• Improving Graph Generation by Restricting Graph Bandwidth
• Rethinking Explaining Graph Neural Networks via Non-parametric Subgraph Matching
• Efficiently predicting high resolution mass spectra with graph neural networks
• Graph Reinforcement Learning for Network Control via Bi-Level Optimization
• On the Expressive Power of Geometric Graph Neural Networks
• Boosting Graph Contrastive Learning via Graph Contrastive Saliency
• Reducing SO(3) Convolutions to SO(2) for Efficient Equivariant GNNs
• DRew: Dynamically Rewired Message Passing with Delay
• TIDE: Time Derivative Diffusion for Deep Learning on Graphs
• Linkless Link Prediction via Relational Distillation
• A Group Symmetric Stochastic Differential Equation Model for Molecule Multi-modal Pretraining
• Learning Compiler Pass Orders using Coreset and Normalized Value Prediction
• SlotGAT: Slot-based Message Passing for Heterogeneous Graphs
• Efficient Learning of Mesh-Based Physical Simulation with Bi-Stride Multi-Scale Graph Neural Network
• Scalable Multi-Agent Reinforcement Learning through Intelligent Information Aggregation
• Disentangled Multiplex Graph Representation Learning
• AbODE: Ab initio antibody design using conjoined ODEs
• Rethinking Weak Supervision in Helping Contrastive Learning
• When and How Does Known Class Help Discover Unknown Ones? Provable Understanding Through Spectral Analysis
• Neural Algorithmic Reasoning with Causal Regularisation
• Towards Robust Graph Incremental Learning on Evolving Graphs
• Transformers Meet Directed Graphs
• Graph Neural Networks can Recover the Hidden Features Solely from the Graph Structure
• Ske2Grid: Skeleton-to-Grid Representation Learning for Action Recognition
• Spatial-Temporal Graph Learning with Adversarial Contrastive Adaptation
• On Over-Squashing in Message Passing Neural Networks: The Impact of Width, Depth, and Topology
• Personalized Subgraph Federated Learning
• Learning Subpocket Prototypes for Generalizable Structure-based Drug Design
• Graph Contrastive Backdoor Attacks
• LazyGNN: Large-Scale Graph Neural Networks via Lazy Propagation
• From Relational Pooling to Subgraph GNNs: A Universal Framework for More Expressive Graph Neural Networks
• RGE: A Repulsive Graph Rectification for Node Classification via Influence
• GOAT: A Global Transformer on Large-scale Graphs
• GraphCleaner: Detecting Mislabelled Samples in Popular Graph Learning Benchmarks
• Generated Graph Detection
• Path Neural Networks: Expressive and Accurate Graph Neural Networks
• Equivariant Polynomials for Graph Neural Networks
• GC-Flow: A Graph-Based Flow Network for Effective Clustering
• Feature Expansion for Graph Neural Networks
• Conformal Prediction Sets for Graph Neural Networks
• Autoregressive Diffusion Model for Graph Generation
• Model-Aware Contrastive Learning: Towards Escaping the Dilemmas
• Structural Re-weighting Improves Graph Domain Adaptation
• E(n) Equivariant Message Passing Simplicial Networks
• All in a Row: Compressed Convolution Networks for Graphs
• Total Variation Graph Neural Networks
• Graphically Structured Diffusion Models
• D2Match: Leveraging Deep Learning and Degeneracy for Subgraph Matching
• FusionRetro: Molecule Representation Fusion via In-Context Learning for Retrosynthetic Planning
• Graph Switching Dynamical Systems
• Finding the Missing-half: Graph Complementary Learning for Homophily-prone and Heterophily-prone Graphs
• Leveraging Label Non-Uniformity for Node Classification in Graph Neural Networks
• Vertical Federated Graph Neural Network for Recommender System
• Conditional Graph Information Bottleneck for Molecular Relational Learning
• Personalized Federated Learning with Inferred Collaboration Graphs
• Randomized Schur Complement Views for Graph Contrastive Learning
• Graph Ladling: Shockingly Simple Parallel GNN Training without Intermediate Communication
• Local Vertex Colouring Graph Neural Networks
• Graph Generative Model for Benchmarking Graph Neural Networks
• Learning Representations without Compositional Assumptions
• GNN&GBDT-Guided Fast Optimizing Framework for Large-scale Integer Programming
• Smart Initial Basis Selection for Linear Programs
• Graph Mixup with Soft Alignments
• Do Not Train It: A Linear Neural Architecture Search of Graph Neural Networks
• A Generalization of ViT/MLP-Mixer to Graphs
• Deep Graph Representation Learning and Optimization for Influence Maximization
• On Strengthening and Defending Graph Reconstruction Attack with Markov Chain Approximation
• Efficient and Degree-Guided Graph Generation via Discrete Diffusion Modeling
• Generative Graph Dictionary Learning
• Graph Positional Encoding via Random Feature Propagation
• Towards Understanding Generalization of Graph Neural Networks
• Searching Large Neighborhoods for Integer Linear Programs with Contrastive Learning
• Graph Neural Networks with Learnable and Optimal Polynomial Bases
• Expectation-Complete Graph Representations with Homomorphisms
• Bayesian Progressive Deep Topic Model with Knowledge Informed Textual Data Coarsening Process
• Universal Morphology Control via Contextual Modulation
• Towards Deep Attention in Graph Neural Networks: Problems and Remedies
• Efficient Approximations of Complete Interatomic Potentials for Crystal Property Prediction
• Improving Graph Neural Networks with Learnable Propagation Operators
• MG-GNN: Multigrid Graph Neural Networks for Learning Multilevel Domain Decomposition Methods
• StriderNet: A Graph Reinforcement Learning Approach to Optimize Atomic Structures on Rough Energy Landscapes
• Half-Hop: A graph upsampling approach for slowing down message passing
• Efficient and Equivariant Graph Networks for Predicting Quantum Hamiltonian
• Uncertainty Estimation for Molecules: Desiderata and Methods
• Towards Quantum Machine Learning for Constrained Combinatorial Optimization: a Quantum QAP Solver
• Featured Graph Coarsening with Similarity Guarantees
• Fisher Information Embedding for Node and Graph Learning
• CoCo: A Coupled Contrastive Framework for Unsupervised Domain Adaptive Graph Classification
• Von Mises Mixture Distributions for Molecular Conformation Generation
• Modeling Dynamic Environments with Scene Graph Memory
• Understanding Oversquashing in GNNs through the Lens of Effective Resistance
• GREAD: Graph Neural Reaction-Diffusion Networks
• Alternately Optimized Graph Neural Networks
• Ewald-based Long-Range Message Passing for Molecular Graphs
• Implicit Graph Neural Networks: A Monotone Operator Viewpoint
• HOPE: High-order Graph ODE For Modeling Interacting Dynamics
• When Sparsity Meets Contrastive Models: Less Graph Data Can Bring Better Class-Balanced Representations
• On the Connection Between MPNN and Graph Transformer
• Learning Preconditioners for Conjugate Gradient PDE Solvers
• SeedGNN: Graph Neural Network for Supervised Seeded Graph Matching
• Graph Inductive Biases in Transformers without Message Passing
• LinSATNet: The Positive Linear Satisfiability Neural Networks
• Exphormer: Sparse Transformers for Graphs
• Wasserstein Barycenter Matching for Graph Size Generalization of Message Passing Neural Networks
• Beyond Homophily: Reconstructing Structure for Graph-agnostic Clustering
• Towards Better Graph Representation Learning with Parameterized Decomposition & Filtering
• SEGA: Structural Entropy Guided Anchor View for Graph Contrastive Learning
• A Complete Expressiveness Hierarchy for Subgraph GNNs via Subgraph Weisfeiler-Lehman Tests
• From Hypergraph Energy Functions to Hypergraph Neural Networks
• Generalizing Neural Wave Functions
• Hierarchical Grammar-Induced Geometry for Data-Efficient Molecular Property Prediction
• InGram: Inductive Knowledge Graph Embedding via Relation Graphs

-------------------------------------------------------------------

ACL 2023 (Jul)

• Joint Constrained Learning with Boundary-adjusting for Emotion-Cause Pair Extraction
• TECHS: Temporal Logical Graph Networks for Explainable Extrapolation Reasoning
• Helping a Friend or Supporting a Cause? Disentangling Active and Passive Cosponsorship in the U.S. Congress
• Peer-Label Assisted Hierarchical Text Classification
• Enhancing Dialogue Generation via Dynamic Graph Knowledge Aggregation
• Enhancing Language Representation with Constructional Information for Natural Language Understanding
• IM-TQA: A Chinese Table Question Answering Dataset with Implicit and Multi-type Table Structures
• Clinical Note Owns its Hierarchy: Multi-Level Hypergraph Neural Networks for Patient-Level Representation Learning
• Curriculum Learning for Graph Neural Networks: A Multiview Competence-based Approach
• DualGATs: Dual Graph Attention Networks for Emotion Recognition in Conversations

more

• Modeling Structural Similarities between Documents for Coherence Assessment with Graph Convolutional Networks
• Dual Class Knowledge Propagation Network for Multi-label Few-shot Intent Detection
• Knowledgeable Parameter Efficient Tuning Network for Commonsense Question Answering
• Just Like a Human Would, Direct Access to Sarcasm Augmented with Potential Result and Reaction
• Multilingual Knowledge Graph Completion with Language-Sensitive Multi-Graph Attention
• Are Message Passing Neural Networks Really Helpful for Knowledge Graph Completion?
• CHEER: Centrality-aware High-order Event Reasoning Network for Document-level Event Causality Identification
• A Novel Table-to-Graph Generation Approach for Document-Level Joint Entity and Relation Extraction
• Semantic Structure Enhanced Event Causality Identification
• Single Sequence Prediction over Reasoning Graphs for Multi-hop QA
• Transforming Visual Scene Graphs to Image Captions
• An AMR-based Link Prediction Approach for Document-level Event Argument Extraction
• DiSCoMaT: Distantly Supervised Composition Extraction from Tables in Materials Science Articles
• Dynamic Heterogeneous-Graph Reasoning with Language Models and Knowledge Representation Learning for Commonsense Question Answering
• Double-Branch Multi-Attention based Graph Neural Network for Knowledge Graph Completion
• KALM: Knowledge-Aware Integration of Local, Document, and Global Contexts for Long Document Understanding
• Cross2StrA: Unpaired Cross-lingual Image Captioning with Cross-lingual Cross-modal Structure-pivoted Alignment
• TREA: Tree-Structure Reasoning Schema for Conversational Recommendation
• CATS: A Pragmatic Chinese Answer-to-Sequence Dataset with Large Scale and High Quality
• History Semantic Graph Enhanced Conversational KBQA with Temporal Information Modeling
• Counterfactual Multihop QA: A Cause-Effect Approach for Reducing Disconnected Reasoning
• Scene Graph as Pivoting: Inference-time Image-free Unsupervised Multimodal Machine Translation with Visual Scene Hallucination
• Patton: Language Model Pretraining on Text-Rich Networks
• Linguistic representations for fewer-shot relation extraction across domains
• Generating Visual Spatial Description via Holistic 3D Scene Understanding
• HAHE: Hierarchical Attention for Hyper-Relational Knowledge Graphs in Global and Local Level
• ORGAN: Observation-Guided Radiology Report Generation via Tree Reasoning
• CASE: Aligning Coarse-to-Fine Cognition and Affection for Empathetic Response Generation
• FormNetV2: Multimodal Graph Contrastive Learning for Form Document Information Extraction
• BIC: Twitter Bot Detection with Text-Graph Interaction and Semantic Consistency
• Multi-source Semantic Graph-based Multimodal Sarcasm Explanation Generation
• Constrained Tuple Extraction with Interaction-Aware Network
• GIFT: Graph-Induced Fine-Tuning for Multi-Party Conversation Understanding
• Learning Latent Relations for Temporal Knowledge Graph Reasoning
• Exploring and Verbalizing Academic Ideas by Concept Co-occurrence
• A Cross-Modality Context Fusion and Semantic Refinement Network for Emotion Recognition in Conversation
• Dense-ATOMIC: Towards Densely-connected ATOMIC with High Knowledge Coverage and Massive Multi-hop Paths
• Holistic Prediction on a Time-Evolving Attributed Graph
• Dialogue Summarization with Static-Dynamic Structure Fusion Graph
• Graph-based Relation Mining for Context-free Out-of-vocabulary Word Embedding Learning
• Information Screening whilst Exploiting! Multimodal Relation Extraction with Feature Denoising and Multimodal Topic Modeling
• Evaluate AMR Graph Similarity via Self-supervised Learning
• Trading Syntax Trees for Wordpieces: Target-oriented Opinion Words Extraction with Wordpieces and Aspect Enhancement
• HiPool: Modeling Long Documents Using Graph Neural Networks
• Simple Augmentations of Logical Rules for Neuro-Symbolic Knowledge Graph Completion

-------------------------------------------------------------------

CVPR 2023 (Jun)

• From Node Interaction To Hop Interaction: New Effective and Scalable Graph Learning Paradigm
• Turning Strengths Into Weaknesses: A Certified Robustness Inspired Attack Framework Against Graph Neural Networks
• Multivariate, Multi-Frequency and Multimodal: Rethinking Graph Neural Networks for Emotion Recognition in Conversation
• Graph Representation for Order-Aware Visual Transformation
• Semi-Weakly Supervised Object Kinematic Motion Prediction
• DiffCollage: Parallel Generation of Large Content With Diffusion Models
• Transductive Few-Shot Learning With Prototype-Based Label Propagation by Iterative Graph Refinement
• Feature Shrinkage Pyramid for Camouflaged Object Detection With Transformers
• Devil's on the Edges: Selective Quad Attention for Scene Graph Generation
• Robust 3D Shape Classification via Non-Local Graph Attention Network

more

• An Actor-Centric Causality Graph for Asynchronous Temporal Inference in Group Activity
• Histopathology Whole Slide Image Analysis With Heterogeneous Graph Representation Learning
• Uncovering the Missing Pattern: Unified Framework Towards Trajectory Imputation and Prediction
• VectorFloorSeg: Two-Stream Graph Attention Network for Vectorized Roughcast Floorplan Segmentation
• 3D Spatial Multimodal Knowledge Accumulation for Scene Graph Prediction in Point Cloud
• Graph Transformer GANs for Graph-Constrained House Generation
• Multi-Object Manipulation via Object-Centric Neural Scattering Functions
• Dynamic Graph Enhanced Contrastive Learning for Chest X-Ray Report Generation
• SViTT: Temporal Learning of Sparse Video-Text Transformers
• High Fidelity 3D Hand Shape Reconstruction via Scalable Graph Frequency Decomposition
• Target-Referenced Reactive Grasping for Dynamic Objects
• Sparse Multi-Modal Graph Transformer With Shared-Context Processing for Representation Learning of Giga-Pixel Images
• Visual Dependency Transformers: Dependency Tree Emerges From Reversed Attention
• Incremental 3D Semantic Scene Graph Prediction From RGB Sequences
• Edge-Aware Regional Message Passing Controller for Image Forgery Localization
• Neural Koopman Pooling: Control-Inspired Temporal Dynamics Encoding for Skeleton-Based Action Recognition
• Sampling Is Matter: Point-Guided 3D Human Mesh Reconstruction
• TranSG: Transformer-Based Skeleton Graph Prototype Contrastive Learning With Structure-Trajectory Prompted Reconstruction for Person Re-Identification
• Deep Learning of Partial Graph Matching via Differentiable Top-K
• Learning and Aggregating Lane Graphs for Urban Automated Driving
• VL-SAT: Visual-Linguistic Semantics Assisted Training for 3D Semantic Scene Graph Prediction in Point Cloud
• ViPLO: Vision Transformer Based Pose-Conditioned Self-Loop Graph for Human-Object Interaction Detection
• Local Connectivity-Based Density Estimation for Face Clustering
• Multilateral Semantic Relations Modeling for Image Text Retrieval
• Adaptive Graph Convolutional Subspace Clustering
• DepGraph: Towards Any Structural Pruning
• FJMP: Factorized Joint Multi-Agent Motion Prediction Over Learned Directed Acyclic Interaction Graphs
• Adversarially Robust Neural Architecture Search for Graph Neural Networks
• IS-GGT: Iterative Scene Graph Generation With Generative Transformers
• Deep Graph-Based Spatial Consistency for Robust Non-Rigid Point Cloud Registration
• SuperDisco: Super-Class Discovery Improves Visual Recognition for the Long-Tail
• KiUT: Knowledge-Injected U-Transformer for Radiology Report Generation
• Progressive Neighbor Consistency Mining for Correspondence Pruning
• MeMaHand: Exploiting Mesh-Mano Interaction for Single Image Two-Hand Reconstruction
• Weakly Supervised Posture Mining for Fine-Grained Classification
• Improving Graph Representation for Point Cloud Segmentation via Attentive Filtering
• Learning Discriminative Representations for Skeleton Based Action Recognition
• Probabilistic Debiasing of Scene Graphs
• Unifying Short and Long-Term Tracking With Graph Hierarchies
• Dynamic Graph Learning With Content-Guided Spatial-Frequency Relation Reasoning for Deepfake Detection
• Tree Instance Segmentation With Temporal Contour Graph
• Mind the Label Shift of Augmentation-Based Graph OOD Generalization
• 3Mformer: Multi-Order Multi-Mode Transformer for Skeletal Action Recognition
• Deep Graph Reprogramming
• Pix2map: Cross-Modal Retrieval for Inferring Street Maps From Images
• HS-Pose: Hybrid Scope Feature Extraction for Category-Level Object Pose Estimation
• Learning Situation Hyper-Graphs for Video Question Answering
• PointDistiller: Structured Knowledge Distillation Towards Efficient and Compact 3D Detection
• TopDiG: Class-Agnostic Topological Directional Graph Extraction From Remote Sensing Images
• CIGAR: Cross-Modality Graph Reasoning for Domain Adaptive Object Detection
• HOOD: Hierarchical Graphs for Generalized Modelling of Clothing Dynamics

-------------------------------------------------------------------

TheWebConf 2023 (Apr)

• Graph Neural Networks with Diverse Spectral Filtering
• Graph Neural Networks without Propagation
• Rethinking Structural Encodings: Adaptive Graph Transformer for Node Classification Task
• Node-wise Diffusion for Scalable Graph Learning
• Unifying and Improving Graph Convolutional Neural Networks with Wavelet Denoising Filters
• CurvDrop: A Ricci Curvature Based Approach to Prevent Graph Neural Networks from Over-Smoothing and Over-Squashing
• Unnoticeable Backdoor Attacks on Graph Neural Networks
• Self-Supervised Teaching and Learning of Representations on Graphs
• Search to Capture Long-range Dependency with Stacking GNNs for Graph Classification
• Generating Counterfactual Hard Negative Samples for Graph Contrastive Learning
• Instance Relation Graph Guided Source-Free Domain Adaptive Object Detection

more

• HyConvE: A Novel Embedding Model for Knowledge Hypergraph Link Prediction with Convolutional Neural Networks
• Unsupervised Anomaly Detection on Microservice Traces through Graph VAE
• Dynamically Expandable Graph Convolution for Streaming Recommendation
• Attacking Fake News Detectors via Manipulating News Social Engagement
• Link Prediction on Latent Heterogeneous Graphs
• Hierarchy-Aware Multi-Hop Question Answering over Knowledge Graphs
• Denoising and Prompt-Tuning for Multi-Behavior Recommendation
• Hierarchical Knowledge Graph Learning Enabled Socioeconomic Indicator Prediction in Location-Based Social Network
• Hierarchical Self-Attention Embedding for Temporal Knowledge Graph Completion
• GraphMAE2: A Decoding-Enhanced Masked Self-Supervised Graph Learner
• Multi-head Variational Graph Autoencoder Constrained by Sum-product Networks
• Robust Mid-Pass Filtering Graph Convolutional Networks
• GraphPrompt: Unifying Pre-Training and Downstream Tasks for Graph Neural Networks
• Robust Graph Representation Learning for Local Corruption Recovery
• Predicting the Silent Majority on Graphs: Knowledge Transferable Graph Neural Network
• Auto-HeG: Automated Graph Neural Network on Heterophilic Graphs
• HINormer: Representation Learning On Heterogeneous Information Networks with Graph Transformer
• Enhancing Hierarchy-Aware Graph Networks with Deep Dual Clustering for Session-based Recommendation
• Detecting Socially Abnormal Highway Driving Behaviors via Recurrent Graph Attention Networks
• Mutually-paced Knowledge Distillation for Cross-lingual Temporal Knowledge Graph Reasoning
• ApeGNN: Node-Wise Adaptive Aggregation in GNNs for Recommendation
• Meta-Learning Based Knowledge Extrapolation for Temporal Knowledge Graph
• Semi-decentralized Federated Ego Graph Learning for Recommendation
• Hashtag-Guided Low-Resource Tweet Classification
• KGTrust: Evaluating Trustworthiness of SIoT via Knowledge Enhanced Graph Neural Networks
• Learning Long- and Short-term Representations for Temporal Knowledge Graph Reasoning
• Interaction-level Membership Inference Attack Against Federated Recommender Systems
• Automated Self-Supervised Learning for Recommendation
• KRACL: Contrastive Learning with Graph Context Modeling for Sparse Knowledge Graph Completion
• HGWaveNet: A Hyperbolic Graph Neural Network for Temporal Link Prediction
• Federated Node Classification over Graphs with Latent Link-type Heterogeneity
• Message Function Search for Knowledge Graph Embedding
• SeeGera: Self-supervised Semi-implicit Graph Variational Auto-encoders with Masking
• Fair Graph Representation Learning via Diverse Mixture-of-Experts
• Graph Neural Network with Two Uplift Estimators for Label-Scarcity Individual Uplift Modeling
• ConsRec: Learning Consensus Behind Interactions for Group Recommendation
• xGCN: An Extreme Graph Convolutional Network for Large-scale Social Link Prediction
• TIGER: Temporal Interaction Graph Embedding with Restarts
• INCREASE: Inductive Graph Representation Learning for Spatio-Temporal Kriging
• Personalized Graph Signal Processing for Collaborative Filtering
• Knowledge Graph Completion with Counterfactual Augmentation
• Structure Pretraining and Prompt Tuning for Knowledge Graph Transfer
• RSGNN: A Model-agnostic Approach for Enhancing the Robustness of Signed Graph Neural Networks
• Minimum Topology Attacks for Graph Neural Networks
• Attribute-Consistent Knowledge Graph Representation Learning for Multi-Modal Entity Alignment
• TEA: Time-aware Entity Alignment in Knowledge Graphs
• Automated Spatio-Temporal Graph Contrastive Learning
• Unlearning Graph Classifiers with Limited Data Resources
• PaGE-Link: Path-based Graph Neural Network Explanation for Heterogeneous Link Prediction
• Multi-Behavior Recommendation with Cascading Graph Convolution Networks
• Multi-Aspect Heterogeneous Graph Augmentation
• TFE-GNN: A Temporal Fusion Encoder Using Graph Neural Networks for Fine-grained Encrypted Traffic Classification
• Learning To Rank Resources with GNN
• Addressing Heterophily in Graph Anomaly Detection: A Perspective of Graph Spectrum
• SE-GSL: A General and Effective Graph Structure Learning Framework through Structural Entropy Optimization
• Intra and Inter Domain HyperGraph Convolutional Network for Cross-Domain Recommendation
• Hyperbolic Geometric Graph Representation Learning for Hierarchy-imbalance Node Classification
• GIF: A General Graph Unlearning Strategy via Influence Function
• Expressive and Efficient Representation Learning for Ranking Links in Temporal Graphs
• Compressed Interaction Graph based Framework for Multi-behavior Recommendation
• Graph-based Village Level Poverty Identification
• Graph Self-supervised Learning with Augmentation-aware Contrastive Learning
• SeqCare: Sequential Training with External Medical Knowledge Graph for Diagnosis Prediction in Healthcare Data
• Bipartite Graph Convolutional Hashing for Effective and Efficient Top-N Search in Hamming Space
• Graph-less Collaborative Filtering
• Encoding Node Diffusion Competence and Role Significance for Network Dismantling
• Knowledge Graph Question Answering with Ambiguous Query
• Label Information Enhanced Fraud Detection against Low Homophily in Graphs
• Unsupervised Entity Alignment for Temporal Knowledge Graphs
• CogDL: A Comprehensive Library for Graph Deep Learning
• A Post-Training Framework for Improving Heterogeneous Graph Neural Networks
• Curriculum Graph Poisoning
• Homophily-oriented Heterogeneous Graph Rewiring
• CMINet: a Graph Learning Framework for Content-aware Multi-channel Influence Diffusion
• Correlative Preference Transfer with Hierarchical Hypergraph Network for Multi-Domain Recommendation
• Robust Preference-Guided Denoising for Graph based Social Recommendation
• Collaboration-Aware Graph Convolutional Network for Recommender Systems
• Dual Intent Enhanced Graph Neural Network for Session-based New Item Recommendation
• Anti-FakeU: Defending Shilling Attacks on Graph Neural Network based Recommender Model
• CitationSum: Citation-aware Graph Contrastive Learning for Scientific Paper Summarization
• Link Prediction with Attention Applied on Multiple Knowledge Graph Embedding Models

-------------------------------------------------------------------

ICLR 2023 (Apr)

• Rethinking the Expressive Power of GNNs via Graph Biconnectivity
• Graph Neural Networks for Link Prediction with Subgraph Sketching
• Do We Really Need Complicated Model Architectures For Temporal Networks?
• Towards Open Temporal Graph Neural Networks
• Learning on Large-scale Text-attributed Graphs via Variational Inference
• Conditional Antibody Design as 3D Equivariant Graph Translation
• Relative representations enable zero-shot latent space communication
• AutoGT: Automated Graph Transformer Architecture Search
• Transfer NAS with Meta-learned Bayesian Surrogates

more

• DIFFormer: Scalable (Graph) Transformers Induced by Energy Constrained Diffusion
• Unbiased Stochastic Proximal Solver for Graph Neural Networks with Equilibrium States
• MLPInit: Embarrassingly Simple GNN Training Acceleration with MLP Initialization
• LMC: Fast Training of GNNs via Subgraph Sampling with Provable Convergence
• Graph Neural Network-Inspired Kernels for Gaussian Processes in Semi-Supervised Learning
• Serving Graph Compression for Graph Neural Networks
• Joint Edge-Model Sparse Learning is Provably Efficient for Graph Neural Networks
• Gradient Gating for Deep Multi-Rate Learning on Graphs
• NAGphormer: A Tokenized Graph Transformer for Node Classification in Large Graphs
• Searching Lottery Tickets in Graph Neural Networks: A Dual Perspective
• Rethinking Graph Lottery Tickets: Graph Sparsity Matters
• $\rm A^2Q$: Aggregation-Aware Quantization for Graph Neural Networks
• Learnable Graph Convolutional Attention Networks
• Limitless Stability for Graph Convolutional Networks
• A critical look at evaluation of GNNs under heterophily: Are we really making progress?
• Ordered GNN: Ordering Message Passing to Deal with Heterophily and Over-smoothing
• A non-asymptotic analysis of oversmoothing in Graph Neural Networks
• ContraNorm: A Contrastive Learning Perspective on Oversmoothing and Beyond
• Anti-Symmetric DGN: a stable architecture for Deep Graph Networks
• FoSR: First-order spectral rewiring for addressing oversquashing in GNNs
• Are More Layers Beneficial to Graph Transformers?
• Deep Ensembles for Graphs with Higher-order Dependencies
• Graph Domain Adaptation via Theory-Grounded Spectral Regularization
• Sign and Basis Invariant Networks for Spectral Graph Representation Learning
• Specformer: Spectral Graph Neural Networks Meet Transformers
• Unveiling the sampling density in non-uniform geometric graphs
• Spectral Augmentation for Self-Supervised Learning on Graphs
• Simple Yet Effective Graph Contrastive Learning for Recommendation
• Graph Contrastive Learning for Skeleton-based Action Recognition
• A Message Passing Perspective on Learning Dynamics of Contrastive Learning
• Characterizing the Influence of Graph Elements
• Revisiting Graph Adversarial Attack and Defense From a Data Distribution Perspective
• Revisiting Robustness in Graph Machine Learning
• Localized Randomized Smoothing for Collective Robustness Certification
• Chasing All-Round Graph Representation Robustness: Model, Training, and Optimization
• Fundamental Limits in Formal Verification of Message-Passing Neural Networks
• Learning MLPs on Graphs: A Unified View of Effectiveness, Robustness, and Efficiency
• ROCO: A General Framework for Evaluating Robustness of Combinatorial Optimization Solvers on Graphs
• Revocable Deep Reinforcement Learning with Affinity Regularization for Outlier-Robust Graph Matching
• Strategic Classification on Graphs
• Empowering Graph Representation Learning with Test-Time Graph Transformation
• Confidence-Based Feature Imputation for Graphs with Partially Known Features
• Fair Attribute Completion on Graph with Missing Attributes
• Robust Fair Clustering: A Novel Fairness Attack and Defense Framework
• Learning Fair Graph Representations via Automated Data Augmentations
• Global Explainability of GNNs via Logic Combination of Learned Concepts
• Interpretable Geometric Deep Learning via Learnable Randomness Injection
• A Differential Geometric View and Explainability of GNN on Evolving Graphs
• GNNInterpreter: A Probabilistic Generative Model-Level Explanation for Graph Neural Networks
• Explaining Temporal Graph Models through an Explorer-Navigator Framework
• A New Hierarchy of Expressivity for Graph Neural Networks
• Boosting the Cycle Counting Power of Graph Neural Networks with I$^2$-GNNs
• Cycle to Clique (Cy2C) Graph Neural Network: A Sight to See beyond Neighborhood Aggregation
• Agent-based Graph Neural Networks
• Automated Data Augmentations for Graph Classification
• Multi-task Self-supervised Graph Neural Networks Enable Stronger Task Generalization
• Graph Neural Networks are Inherently Good Generalizers: Insights by Bridging GNNs and Multi-Layer Perceptrons
• Improving Out-of-distribution Generalization with Indirection Representations
• Energy-based Out-of-Distribution Detection for Graph Neural Networks
• Control Graph as Unified IO for Morphology-Task Generalization
• GNNDelete: A General Unlearning Strategy for Graph Neural Networks
• Efficient Model Updates for Approximate Unlearning of Graph-Structured Data
• MetaGL: Evaluation-Free Selection of Graph Learning Models via Meta-Learning
• Link Prediction with Non-Contrastive Learning
• GReTo: Remedying dynamic graph topology-task discordance via target homophily
• CUTS: Neural Causal Discovery from Unstructured Time-Series Data
• Logical Message Passing Networks with One-hop Inference on Atomic Formulas
• Learning Heterogeneous Interaction Strengths by Trajectory Prediction with Graph Neural Network
• Leveraging Future Relationship Reasoning for Vehicle Trajectory Prediction
• Edgeformers: Graph-Empowered Transformers for Representation Learning on Textual-Edge Networks
• DiGress: Discrete Denoising diffusion for graph generation
• GOGGLE: Generative Modelling for Tabular Data by Learning Relational Structure
• DAG Matters! GFlowNets Enhanced Explainer for Graph Neural Networks
• GFlowNets and variational inference
• Diffusion Probabilistic Modeling of Protein Backbones in 3D for the motif-scaffolding problem
• Molecule Generation For Target Protein Binding with Structural Motifs
• Learning Harmonic Molecular Representations on Riemannian Manifold
• De Novo Molecular Generation via Connection-aware Motif Mining
• Sampling-free Inference for Ab-Initio Potential Energy Surface Networks
• $\mathcal{O}$-GNN: incorporating ring priors into molecular modeling
• Molecular Geometry Pretraining with SE(3)-Invariant Denoising Distance Matching
• Mole-BERT: Rethinking Pre-training Graph Neural Networks for Molecules
• Pre-training via Denoising for Molecular Property Prediction
• Matching receptor to odorant with protein language and graph neural networks
• PiFold: Toward effective and efficient protein inverse folding
• ModelAngelo: Automated Model Building for Cryo-EM Maps
• Hierarchical Protein Representations via Complete 3D Graph Networks
• Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphs
• Equivariant Hypergraph Diffusion Neural Operators
• A General Framework For Proving The Equivariant Strong Lottery Ticket Hypothesis
• Anisotropic Message Passing: Graph Neural Networks with Directional and Long-Range Interactions
• Equivariant Descriptor Fields: SE(3)-Equivariant Energy-Based Models for End-to-End Visual Robotic Manipulation Learning
• Learnable Topological Features For Phylogenetic Inference via Graph Neural Networks
• Learning Symbolic Models for Graph-structured Physical Mechanism
• ACMP: Allen-Cahn Message Passing with Attractive and Repulsive Forces for Graph Neural Networks
• Learning Controllable Adaptive Simulation for Multi-scale Physics
• Enhancing the Inductive Biases of Graph Neural ODE for Modeling Dynamical Systems
• Grounding Graph Network Simulators using Physical Sensor Observations
• Learning rigid dynamics with face interaction graph networks
• Schema Inference for Interpretable Image Classification
• Learning Domain-Agnostic Representation for Disease Diagnosis
• Pushing the Limits of Fewshot Anomaly Detection in Industry Vision: Graphcore
• Latent Graph Inference using Product Manifolds
• Random Laplacian Features for Learning with Hyperbolic Space
• Dual Algorithmic Reasoning
• Relational Attention: Generalizing Transformers for Graph-Structured Tasks
• Neural DAG Scheduling via One-Shot Priority Sampling
• Unsupervised Learning for Combinatorial Optimization Needs Meta Learning
• Backpropagation through Combinatorial Algorithms: Identity with Projection Works
• Graph-based Deterministic Policy Gradient for Repetitive Combinatorial Optimization Problems
• A GNN-Guided Predict-and-Search Framework for Mixed-Integer Linear Programming
• On Representing Mixed-Integer Linear Programs by Graph Neural Networks
• On Representing Linear Programs by Graph Neural Networks
• Static Prediction of Runtime Errors by Learning to Execute Programs with External Resource Descriptions
• AutoTransfer: AutoML with Knowledge Transfer - An Application to Graph Neural Networks
• Effects of Graph Convolutions in Multi-layer Networks
• Simplicial Hopfield networks
• Learning Hyper Label Model for Programmatic Weak Supervision
• Learning to Solve Constraint Satisfaction Problems with Recurrent Transformers
• Learning to CROSS exchange to solve min-max vehicle routing problems
• Predicting Cellular Responses with Variational Causal Inference and Refined Relational Information
• Graph Signal Sampling for Inductive One-Bit Matrix Completion: a Closed-form Solution
• CktGNN: Circuit Graph Neural Network for Electronic Design Automation
• {EAGLE}: Large-scale Learning of Turbulent Fluid Dynamics with Mesh Transformers

-------------------------------------------------------------------

WSDM 2023 (Mar)

• CLNode: Curriculum Learning for Node Classification
• Robust Training of Graph Neural Networks via Noise Governance
• DisenPOI: Disentangling Sequential and Geographical Influence for Point-of-Interest Recommendation
• Self-Supervised Group Graph Collaborative Filtering for Group Recommendation
• Knowledge-Adaptive Contrastive Learning for Recommendation
• Beyond Individuals: Modeling Mutual and Multiple Interactions for Inductive Link Prediction between Groups
• Modeling Fine-grained Information via Knowledge-aware Hierarchical Graph for Zero-shot Entity Retrieval
• Variational Reasoning over Incomplete Knowledge Graphs for Conversational Recommendation
• GOOD-D: On Unsupervised Graph Out-Of-Distribution Detection
• Towards Faithful and Consistent Explanations for Graph Neural Networks

more

• VRKG4Rec: Virtual Relational Knowledge Graph for Recommendation
• Weakly Supervised Entity Alignment with Positional Inspiration
• Graph Explicit Neural Networks: Explicitly Encoding Graphs for Efficient and Accurate Inference
• Mining User-aware Multi-relations for Fake News Detection in Large Scale Online Social Networks
• Dependency-aware Self-training for Entity Alignment
• MM-GNN: Mix-Moment Graph Neural Network towards Modeling Neighborhood Feature Distribution
• Simplifying Graph-based Collaborative Filtering for Recommendation
• Graph Neural Networks with Interlayer Feature Representation for Image Super-Resolution
• SGCCL: Siamese Graph Contrastive Consensus Learning for Personalized Recommendation
• Simultaneous Linear Multi-view Attributed Graph Representation Learning and Clustering
• Cooperative Explanations of Graph Neural Networks
• A Multi-graph Fusion Based Spatiotemporal Dynamic Learning Framework
• BLADE: Biased Neighborhood Sampling based Graph Neural Network for Directed Graphs
• Bring Your Own View: Graph Neural Networks for Link Prediction with Personalized Subgraph Selection
• Few-shot Node Classification with Extremely Weak Supervision
• Inductive Graph Transformer for Delivery Time Estimation
• S2GAE: Self-Supervised Graph Autoencoders are Generalizable Learners with Graph Masking
• Search Behavior Prediction: A Hypergraph Perspective
• Unbiased and Efficient Self-Supervised Incremental Contrastive Learning
• Learning to Distill Graph Neural Networks
• Graph Sequential Neural ODE Process for Link Prediction on Dynamic and Sparse Graphs
• DGRec: Graph Neural Network for Recommendation with Diversified Embedding Generation
• Self-supervised Graph Representation Learning for Black Market Account Detection
• Exploiting Explicit and Implicit Item relationships for Session-based Recommendation
• Efficiently Leveraging Multi-level User Intent for Session-based Recommendation via Atten-Mixer Network
• Alleviating Structural Distribution Shift in Graph Anomaly Detection
• Heterogeneous Graph Contrastive Learning for Recommendation
• Minimum Entropy Principle Guided Graph Neural Networks
• Self-Supervised Graph Structure Refinement for Graph Neural Networks
• Global Counterfactual Explainer for Graph Neural Networks
• Disentangled Negative Sampling for Collaborative Filtering
• Interpretable Research Interest Shift Detection with Temporal Heterogeneous Graphs
• Ranking-based Group Identification via Factorized Attention on Social Tripartite Graph
• Position-Aware Subgraph Neural Networks with Data-Efficient Learning
• Knowledge Enhancement for Contrastive Multi-Behavior Recommendation
• Heterogeneous Graph-based Context-aware Document Ranking

-------------------------------------------------------------------

AAAI 2023 (Feb)

• Beyond Smoothing: Unsupervised Graph Representation Learning with Edge Heterophily Discriminating
• Self-Supervised Continual Graph Learning in Adaptive Riemannian Spaces
• Beyond Graph Convolutional Network: An Interpretable Regularizer-Centered Optimization Framework
• Time-Aware Random Walk Diffusion to Improve Dynamic Graph Learning
• Adversarial Weight Perturbation Improves Generalization in Graph Neural Networks
• Global Concept-Based Interpretability for Graph Neural Networks via Neuron Analysis
• Interpolating Graph Pair to Regularize Graph Classification
• Boosting Graph Neural Networks via Adaptive Knowledge Distillation
• Spectral Feature Augmentation for Graph Contrastive Learning and Beyond
• Substructure Aware Graph Neural Networks

more

• Learnable Spectral Wavelets on Dynamic Graphs to Capture Global Interactions
• GLCC: A General Framework for Graph-Level Clustering
• Scaling Up Dynamic Graph Representation Learning via Spiking Neural Networks
• Generalizing Downsampling from Regular Data to Graphs
• DHGE: Dual-View Hyper-Relational Knowledge Graph Embedding for Link Prediction and Entity Typing
• Simple and Efficient Heterogeneous Graph Neural Network
• Graph Ordering Attention Networks
• Let Graph Be the Go Board: Gradient-Free Node Injection Attack for Graph Neural Networks via Reinforcement Learning
• Where Will Players Move Next? Dynamic Graphs and Hierarchical Fusion for Movement Forecasting in Badminton
• Interpreting Unfairness in Graph Neural Networks via Training Node Attribution
• Spatio-Temporal Meta-Graph Learning for Traffic Forecasting
• Differentiable Meta Multigraph Search with Partial Message Propagation on Heterogeneous Information Networks
• Heterogeneous Graph Learning for Multi-Modal Medical Data Analysis
• Lifelong Embedding Learning and Transfer for Growing Knowledge Graphs
• Linking Sketch Patches by Learning Synonymous Proximity for Graphic Sketch Representation
• GENNAPE: Towards Generalized Neural Architecture Performance Estimators
• AIO-P: Expanding Neural Performance Predictors beyond Image Classification
• Unbiased Heterogeneous Scene Graph Generation with Relation-Aware Message Passing Neural Network
• Graph Anomaly Detection via Multi-Scale Contrastive Learning Networks with Augmented View
• Universe Points Representation Learning for Partial Multi-Graph Matching
• Knowledge-Bridged Causal Interaction Network for Causal Emotion Entailment
• Spatio-Temporal Self-Supervised Learning for Traffic Flow Prediction
• RWEN-TTS: Relation-Aware Word Encoding Network for Natural Text-to-Speech Synthesis
• Heterogeneous Graph Masked Autoencoders
• T2-GNN: Graph Neural Networks for Graphs with Incomplete Features and Structure via Teacher-Student Distillation
• GraphSR: A Data Augmentation Algorithm for Imbalanced Node Classification
• Exploring Faithful Rationale for Multi-Hop Fact Verification via Salience-Aware Graph Learning
• Wasserstein Graph Distance Based on L1–Approximated Tree Edit Distance between Weisfeiler–Lehman Subtrees
• FTM: A Frame-Level Timeline Modeling Method for Temporal Graph Representation Learning
• Handling Missing Data via Max-Entropy Regularized Graph Autoencoder
• T2G-FORMER: Organizing Tabular Features into Relation Graphs Promotes Heterogeneous Feature Interaction
• Boundary Graph Neural Networks for 3D Simulations
• CrysGNN: Distilling Pre-trained Knowledge to Enhance Property Prediction for Crystalline Materials
• Restructuring Graph for Higher Homophily via Adaptive Spectral Clustering
• Deep Graph Structural Infomax
• Hard Sample Aware Network for Contrastive Deep Graph Clustering
• Robust Causal Graph Representation Learning against Confounding Effects
• DropMessage: Unifying Random Dropping for Graph Neural Networks
• Relation-Aware Language-Graph Transformer for Question Answering
• Reviewing Labels: Label Graph Network with Top-k Prediction Set for Relation Extraction
• A Graph Fusion Approach for Cross-Lingual Machine Reading Comprehension
• Data Imputation with Iterative Graph Reconstruction
• Federated Learning on Non-IID Graphs via Structural Knowledge Sharing
• Extracting Low-/High- Frequency Knowledge from Graph Neural Networks and Injecting It into MLPs: An Effective GNN-to-MLP Distillation Framework
• Easy Begun Is Half Done: Spatial-Temporal Graph Modeling with ST-Curriculum Dropout
• Joint Multimodal Entity-Relation Extraction Based on Edge-Enhanced Graph Alignment Network and Word-Pair Relation Tagging
• Self-Supervised Learning for Anomalous Channel Detection in EEG Graphs: Application to Seizure Analysis
• Graphix-T5: Mixing Pre-trained Transformers with Graph-Aware Layers for Text-to-SQL Parsing
• Improving Interpretability via Explicit Word Interaction Graph Layer
• Entity-Agnostic Representation Learning for Parameter-Efficient Knowledge Graph Embedding
• LIMIP: Lifelong Learning to Solve Mixed Integer Programs
• GRLSTM: Trajectory Similarity Computation with Graph-Based Residual LSTM
• Compressed Heterogeneous Graph for Abstractive Multi-Document Summarization
• Context-Aware Safe Medication Recommendations with Molecular Graph and DDI Graph Embedding
• Topological Pooling on Graphs
• Dynamic Heterogeneous Graph Attention Neural Architecture Search
• Self-Supervised Bidirectional Learning for Graph Matching
• KerPrint: Local-Global Knowledge Graph Enhanced Diagnosis Prediction for Retrospective and Prospective Interpretations
• Cogito Ergo Summ: Abstractive Summarization of Biomedical Papers via Semantic Parsing Graphs and Consistency Rewards
• Latent Constraints on Unsupervised Text-Graph Alignment with Information Asymmetry
• Cross-Domain Few-Shot Graph Classification with a Reinforced Task Coordinator
• Local-Global Defense against Unsupervised Adversarial Attacks on Graphs
• Dual Label-Guided Graph Refinement for Multi-View Graph Clustering
• Learning Decomposed Spatial Relations for Multi-Variate Time-Series Modeling
• Structure Aware Incremental Learning with Personalized Imitation Weights for Recommender Systems
• Self-Supervised Graph Attention Networks for Deep Weighted Multi-View Clustering
• Orders Are Unwanted: Dynamic Deep Graph Convolutional Network for Personality Detection
• Self-Organization Preserved Graph Structure Learning with Principle of Relevant Information
• SigMaNet: One Laplacian to Rule Them All
• Predicting Temporal Sets with Simplified Fully Connected Networks
• Learning Topology-Specific Experts for Molecular Property Prediction
• Eliciting Structural and Semantic Global Knowledge in Unsupervised Graph Contrastive Learning
• PDFormer: Propagation Delay-Aware Dynamic Long-Range Transformer for Traffic Flow Prediction
• Multi-Level Confidence Learning for Trustworthy Multimodal Classification
• Graph Structure Learning on User Mobility Data for Social Relationship Inference
• Enhanced Multi-Relationships Integration Graph Convolutional Network for Inferring Substitutable and Complementary Items
• Dual Memory Units with Uncertainty Regulation for Weakly Supervised Video Anomaly Detection
• Multi-Relational Contrastive Learning Graph Neural Network for Drug-Drug Interaction Event Prediction
• MulGT: Multi-Task Graph-Transformer with Task-Aware Knowledge Injection and Domain Knowledge-Driven Pooling for Whole Slide Image Analysis
• Augmenting Affective Dependency Graph via Iterative Incongruity Graph Learning for Sarcasm Detection
• Learning from Good Trajectories in Offline Multi-Agent Reinforcement Learning
• DrugOOD: Out-of-Distribution Dataset Curator and Benchmark for AI-Aided Drug Discovery – a Focus on Affinity Prediction Problems with Noise Annotations
• A Set of Control Points Conditioned Pedestrian Trajectory Prediction
• Towards Complex Scenarios: Building End-to-End Task-Oriented Dialogue System across Multiple Knowledge Bases
• Random Walk Conformer: Learning Graph Representation from Long and Short Range
• Continual Graph Convolutional Network for Text Classification
• Dual Low-Rank Graph Autoencoder for Semantic and Topological Networks
• Frame-Level Label Refinement for Skeleton-Based Weakly-Supervised Action Recognition
• AlphaRoute: Large-Scale Coordinated Route Planning via Monte Carlo Tree Search
• Leveraging Weighted Cross-Graph Attention for Visual and Semantic Enhanced Video Captioning Network
• Scalable Attributed-Graph Subspace Clustering
• Graph Knows Unknowns: Reformulate Zero-Shot Learning as Sample-Level Graph Recognition
• Towards Fine-Grained Explainability for Heterogeneous Graph Neural Network
• Self-Supervised Learning for Multilevel Skeleton-Based Forgery Detection via Temporal-Causal Consistency of Actions
• Novel Motion Patterns Matter for Practical Skeleton-Based Action Recognition
• GMDNet: A Graph-Based Mixture Density Network for Estimating Packages’ Multimodal Travel Time Distribution
• WaveForM: Graph Enhanced Wavelet Learning for Long Sequence Forecasting of Multivariate Time Series
• USER: Unsupervised Structural Entropy-Based Robust Graph Neural Network
• Learning from the Wisdom of Crowds: Exploiting Similar Sessions for Session Search
• Signed Laplacian Graph Neural Networks
• Gradient-Based Graph Attention for Scene Text Image Super-resolution
• DRGCN: Dynamic Evolving Initial Residual for Deep Graph Convolutional Networks
• GRIP: Graph Representation of Immune Repertoire Using Graph Neural Network and Transformer
• Learning to Count Isomorphisms with Graph Neural Networks
• Multi-Domain Generalized Graph Meta Learning
• Scalable Spatiotemporal Graph Neural Networks
• Asynchronous Event Processing with Local-Shift Graph Convolutional Network
• Social Relation Reasoning Based on Triangular Constraints
• On Generalized Degree Fairness in Graph Neural Networks
• Attribute and Structure Preserving Graph Contrastive Learning
• Inferring Patient Zero on Temporal Networks via Graph Neural Networks
• Neighbor Contrastive Learning on Learnable Graph Augmentation

-------------------------------------------------------------------

Years: 2022 | 2021 | 2020 | 2019 | 2018 | 2017 and Earlier