THUDM · cenyk1230 · Jul 22, 2022 · Jul 21, 2022 · Jul 21, 2022
diff --git a/README.md b/README.md
@@ -9,7 +9,7 @@
 [![License](https://img.shields.io/github/license/thudm/cogdl)](https://github.com/THUDM/cogdl/blob/master/LICENSE)
 [![Code Style](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/ambv/black)
 
-**[Homepage](https://cogdl.ai)** | **[Paper](https://arxiv.org/abs/2103.00959)** | **[100 GNN papers](./gnn_papers.md)** | **[Leaderboards](./results.md)** | **[Documentation](https://cogdl.readthedocs.io)** | **[Datasets](./cogdl/datasets/README.md)** | **[Join our Slack](https://join.slack.com/t/cogdl/shared_invite/zt-b9b4a49j-2aMB035qZKxvjV4vqf0hEg)** | **[中文](./README_CN.md)**
+**[Homepage](https://cogdl.ai)** | **[Paper](https://arxiv.org/abs/2103.00959)** | **[Documentation](https://cogdl.readthedocs.io)** | **[Discussion Forum](https://discuss.cogdl.ai)** | **[Dataset](./cogdl/datasets/README.md)** | **[中文](./README_CN.md)**
 
 CogDL is a graph deep learning toolkit that allows researchers and developers to easily train and compare baseline or customized models for node classification, graph classification, and other important tasks in the graph domain. 
 
@@ -21,20 +21,22 @@ We summarize the contributions of CogDL as follows:
 
 ## ❗ News
 
+- A free GNN course provided by CogDL Team is present at [this link](https://cogdl.ai/gnn2022/). We also provide a [discussion forum](https://discuss.cogdl.ai) for Chinese users. 
+
 - The new **v0.5.3 release** supports mixed-precision training by setting \textit{fp16=True} and provides a basic [example](https://github.com/THUDM/cogdl/blob/master/examples/jittor/gcn.py) written by [Jittor](https://github.com/Jittor/jittor). It also updates the tutorial in the document, fixes downloading links of some datasets, and fixes potential bugs of operators. 
 
 - The new **v0.5.2 release** adds a GNN example for ogbn-products and updates geom datasets. It also fixes some potential bugs including setting devices, using cpu for inference, etc.
 
 - The new **v0.5.1 release** adds fast operators including SpMM (cpu version) and scatter_max (cuda version). It also adds lots of datasets for node classification which can be found in [this link](./cogdl/datasets/rd2cd_data.py). 🎉
 
-- The new **v0.5.0 release** designs and implements a unified training loop for GNN. It introduces `DataWrapper` to help prepare the training/validation/test data and `ModelWrapper` to define the training/validation/test steps. 🎉
-
 <details>
 <summary>
 News History
 </summary>
 <br/>
 
+- The new **v0.5.0 release** designs and implements a unified training loop for GNN. It introduces `DataWrapper` to help prepare the training/validation/test data and `ModelWrapper` to define the training/validation/test steps. 🎉
+
 - The new **v0.4.1 release** adds the implementation of Deep GNNs and the recommendation task. It also supports new pipelines for generating embeddings and recommendation. Welcome to join our tutorial on KDD 2021 at 10:30 am - 12:00 am, Aug. 14th (Singapore Time). More details can be found in https://kdd2021graph.github.io/. 🎉
 
 - The new **v0.4.0 release** refactors the data storage (from `Data` to `Graph`) and provides more fast operators to speed up GNN training. It also includes many self-supervised learning methods on graphs. BTW, we are glad to announce that we will give a tutorial on KDD 2021 in August. Please see [this link](https://kdd2021graph.github.io/) for more details. 🎉
@@ -110,18 +112,6 @@ def search_space(trial):
 experiment(dataset="cora", model="gcn", seed=[1, 2], search_space=search_space)
 ```
 
-Some interesting applications can be used through `pipeline` API. An example can be found in the [pipeline.py](https://github.com/THUDM/cogdl/tree/master/examples/pipeline.py). 
-
-```python
-from cogdl import pipeline
-
-# load OAGBert model and perform inference
-oagbert = pipeline("oagbert")
-outputs = oagbert(["CogDL is developed by KEG, Tsinghua.", "OAGBert is developed by KEG, Tsinghua."])
-```
-
-More details of the OAGBert usage can be found [here](./cogdl/oag/README.md).
-
 ### Command-Line Usage
 
 You can also use `python scripts/train.py --dataset example_dataset --model example_model` to run example_model on example_data.

diff --git a/README_CN.md b/README_CN.md
@@ -9,7 +9,7 @@
 [![License](https://img.shields.io/github/license/thudm/cogdl)](https://github.com/THUDM/cogdl/blob/master/LICENSE)
 [![Code Style](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/ambv/black)
 
-**[主页](https://cogdl.ai/zh)** | **[论文](https://arxiv.org/abs/2103.00959)** | **[100篇GNN论文](./gnn_papers.md)** | **[排行榜](./results.md)** | **[文档](https://cogdl.readthedocs.io)** | **[数据集](./cogdl/datasets/README.md)** | **[加入我们的Slack](https://join.slack.com/t/cogdl/shared_invite/zt-b9b4a49j-2aMB035qZKxvjV4vqf0hEg)** | **[English](./README.md)**
+**[主页](https://cogdl.ai)** | **[论文](https://arxiv.org/abs/2103.00959)** | **[文档](https://cogdl.readthedocs.io)** | **[讨论区](https://discuss.cogdl.ai)** | **[数据集](./cogdl/datasets/README.md)** | **[English](./README.md)**
 
 CogDL是一款图深度学习工具包，基于[PyTorch](https://github.com/pytorch/pytorch)框架。CogDL允许研究人员和开发人员可以轻松地训练和比较基线算法或自定义模型，以进行结点分类，链接预测，图分类，社区发现等基于图结构的任务。 它提供了许多流行模型的实现，包括：非图神经网络算法例如Deepwalk、LINE、Node2vec、NetMF、ProNE、methpath2vec、PTE、graph2vec、DGK等；图神经网络算法例如GCN、GAT、GraphSAGE、FastGCN、GTN、HAN、GIN、DiffPool等。它也提供了一些下游任务，包括结点分类（分为是否具有节点属性），链接预测（分为同构和异构），图分类（分有监督和⽆监督）以及为这些任务构建各种算法效果的排行榜。
 
@@ -21,20 +21,22 @@ CogDL的特性包括：
 
 ## ❗ 最新
 
+- CogDL团队为大家开设了一门免费的GNN课程，大家可以访问[这个链接](https://cogdl.ai/gnn2022/)来获取。我们为大家提供了一个[讨论区](https://discuss.cogdl.ai)来进行交流。 
+
 - 最新的 **v0.5.3 release** 支持混合精度(fp16)训练，提供了[Jittor](https://github.com/Jittor/jittor)的初步支持（见[example](https://github.com/THUDM/cogdl/blob/master/examples/jittor/gcn.py)）。这个版本更新了文档中的使用教程，修复了一部分数据集的下载链接，修复了某些算子在不同环境下可能的问题。
 
 - 最新的 **v0.5.2 release** 给ogbn-products数据集添加了GNN样例，更新了geom数据集。这个版本同时修复了一些潜在的问题，包括设置不同device，使用cpu进行预测等。
 
 - 最新的 **v0.5.1 release** 添加了一些高效的算子，包括cpu版本的SpMM和cuda版本的scatter_max。这个版本同时增加了很多用于节点分类的[数据集](./cogdl/datasets/rd2cd_data.py)。 🎉
 
-- 最新的 **v0.5.0 release** 为图神经网络的训练设计了一套统一的流程. 这个版本去除了原先的`Task`类，引入了`DataWrapper`来准备training/validation/test过程中所需的数据，引入了`ModelWrapper`来定义模型training/validation/test的步骤. 🎉
-
 <details>
 <summary>
 历史
 </summary>
 <br/>
 
+- 最新的 **v0.5.0 release** 为图神经网络的训练设计了一套统一的流程. 这个版本去除了原先的`Task`类，引入了`DataWrapper`来准备training/validation/test过程中所需的数据，引入了`ModelWrapper`来定义模型training/validation/test的步骤. 🎉
+
 - 最新的 **v0.4.1 release** 增加了深层GNN的实现和推荐任务。这个版本同时提供了新的一些pipeline用于直接获取图表示和搭建推荐应用。欢迎大家参加我们在KDD 2021上的tutorial，时间是8月14号上午10:30 - 12:00（北京时间）。 更多的内容可以查看 https://kdd2021graph.github.io/. 🎉
 
 - 最新的 **v0.4.0版本** 重构了底层的数据存储（从`Data`类变为`Graph`类），并且提供了更多快速的算子来加速图神经网络的训练。这个版本还包含了很多图自监督学习的算法。同时，我们很高兴地宣布我们将在8月份的KDD 2021会议上给一个CogDL相关的tutorial。具体信息请参见[这个链接](https://kdd2021graph.github.io/). 🎉
@@ -108,18 +110,6 @@ def search_space(trial):
 experiment(dataset="cora", model="gcn", seed=[1, 2], search_space=search_space)
 ```
 
-您也可以通过`pipeline`接口来跑一些有趣的应用。下面这个例子能够在[pipeline.py](https://github.com/THUDM/cogdl/tree/master/examples/pipeline.py)文件中找到。
-
-```python
-from cogdl import pipeline
-
-# load OAGBert model and perform inference
-oagbert = pipeline("oagbert")
-outputs = oagbert(["CogDL is developed by KEG, Tsinghua.", "OAGBert is developed by KEG, Tsinghua."])
-```
-
-有关OAGBert更多的用法可以参见[这里](./cogdl/oag/README.md).
-
 ### 命令行
 基本用法可以使用 `python train.py --dataset example_dataset --model example_model` 来在 `example_data` 上运行 `example_model`。
 

diff --git a/scripts/installation/metis.sh b/scripts/installation/metis.sh
@@ -1,6 +1,6 @@
 file="metis-5.1.0"
 
-wget "http://glaros.dtc.umn.edu/gkhome/fetch/sw/metis/${file}.tar.gz"
+wget https://cloud.tsinghua.edu.cn/f/fd30d629a08645bbbdb8/?dl=1 -O "${file}.tar.gz"
 gunzip "${file}.tar.gz"
 tar -xvf "${file}.tar"