From 07fff7b7e4786d60a29cc7936482b3605c1fe72d Mon Sep 17 00:00:00 2001 From: Daoyuan Chen <67475544+yxdyc@users.noreply.github.com> Date: Thu, 30 Mar 2023 19:32:25 +0800 Subject: [PATCH] update for pFL paper list (#561) --- materials/paper_list/Personalized_FL/README.md | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-) diff --git a/materials/paper_list/Personalized_FL/README.md b/materials/paper_list/Personalized_FL/README.md index df850ecdb..b1fa59442 100644 --- a/materials/paper_list/Personalized_FL/README.md +++ b/materials/paper_list/Personalized_FL/README.md @@ -1,6 +1,16 @@ ## Personalized Federated Learning This list is constantly being updated. Feel free to contribute! +### 2023 +| Title | Venue | Link | Keywords | Note | +| --- | --- | --- | --- | --- | +| Personalized Federated Learning with Feature Alignment and Classifier Collaboration | ICLR | [pdf](https://openreview.net/pdf?id=SXZr8aDKia) | Collaboration | feature alignment by regularization, theoretically-guaranteed heads combination +| Test-Time Robust Personalization for Federated Learning | ICLR | [pdf](https://openreview.net/pdf?id=3aBuJEza5sq) | Test-time Robustness | +| A Statistical Framework for Personalized Federated Learning and Estimation: Theory, Algorithms, and Privacy | ICLR | [pdf](https://openreview.net/pdf?id=FUiDMCr_W4o) | Statistical Estimation, Differential Privacy, Empirical/Hierarchical Bayes | +| FiT: Parameter Efficient Few-shot Transfer Learning for Personalized and Federated Image Classification | ICLR | [pdf](https://openreview.net/pdf?id=9aokcgBVIj1) | few-shot learning, transfer learning | +| PerFedMask: Personalized Federated Learning with Optimized Masking Vectors | ICLR | [pdf](https://openreview.net/pdf?id=hxEIgUXLFF) | Masking vectors | +| The Best of Both Worlds: Accurate Global and Personalized Models through Federated Learning with Data-Free Hyper-Knowledge Distillation | ICLR | [pdf](https://openreview.net/pdf?id=29V3AWjVAFi) | Knowledge Distillation, Differential Privacy, | share means of local data representations and soft predictions; no public data + ### 2022 | Title | Venue | Link | Keywords | Note | | --- | --- | --- | --- | --- | @@ -16,18 +26,18 @@ This list is constantly being updated. Feel free to contribute! | Personalized Federated Learning via Variational Bayesian Inference | ICML | [pdf](https://arxiv.org/pdf/2206.07977.pdf) | Bayesian variational inference; Upper bound | | Federated Learning with Partial Model Personalization | ICML | [pdf](https://proceedings.mlr.press/v162/pillutla22a/pillutla22a.pdf) | Partial model parameters; Transformer | | On Bridging Generic and Personalized Federated Learning for Image Classification | ICLR | [pdf](https://arxiv.org/pdf/2107.00778) | Partial model parameters; | -| FedBABU: Toward Enhanced Representation for Federated Image Classification | ICLR | [pdf](https://openreview.net/pdf?id=HuaYQfggn5u) | Partial model parameters; | +| FedBABU: Toward Enhanced Representation for Federated Image Classification | ICLR | [pdf](https://openreview.net/pdf?id=HuaYQfggn5u) | Partial model parameters; | keep the head (classifer) unchanged during FL training, then conduct fine-tuning before inference | Towards Personalized Federated Learning | Transactions on Neural Networks and Learning Systems | [pdf](https://arxiv.org/pdf/2103.00710)| Survey | ### 2021 | Title | Venue | Link | Keywords | Note | | --- | --- | --- | --- | --- | | Federated muli-task learning under a mixture of distributions | NeurIPS | [pdf](https://arxiv.org/pdf/2108.10252), [code](https://github.com/omarfoq/FedEM) | Distribution Mixture; Expectation-Maximization; FedEM | -| Parameterized Knowledge Transfer for Personalized Federated Learning | NeurIPS | [pdf](https://arxiv.org/pdf/2111.02862) | Knowledge Distillation | +| Parameterized Knowledge Transfer for Personalized Federated Learning | NeurIPS | [pdf](https://arxiv.org/pdf/2111.02862) | Knowledge Distillation | transmit only soft-predictions; public dataset required | Personalized Federated Learning with Gaussian Processes | NeurIPS | [pdf](https://arxiv.org/pdf/2106.15482), [code](https://github.com/IdanAchituve/pFedGP) | Gaussian process; Generalization bound | | Ditto: Fair and robust federated learning through personalization | ICML | [pdf](https://arxiv.org/pdf/2012.04221), [code](https://github.com/litian96/ditto) | Threat model; Fairness; Regularizer | | Personalized Federated Learning using Hypernetworks | ICML | [pdf](https://arxiv.org/pdf/2103.04628), [code](https://github.com/AvivSham/pFedHN) | Hypernetwork; Client Embedding | -| Exploiting Shared Representations for Personalized Federated Learning | ICML | [pdf](https://arxiv.org/pdf/2102.07078.pdf), [code](https://github.com/lgcollins/FedRep) | Partial model parameters | +| Exploiting Shared Representations for Personalized Federated Learning | ICML | [pdf](https://arxiv.org/pdf/2102.07078.pdf), [code](https://github.com/lgcollins/FedRep) | Partial model parameters | FedRep, shared body (feature extractor), personalized head (classifier) | Personalized Federated Learning with First Order Model Optimization | ICLR | [pdf](https://arxiv.org/pdf/2012.08565), [code](https://github.com/NVlabs/FedFomo) | Model mixture | | FedBN: Federated Learning on Non-IID Features via Local Batch Normalization | ICLR | [pdf](https://arxiv.org/pdf/2102.07623), [code](https://github.com/med-air/FedBN) | Partial model parameters |