https://github.com/wangyouze/GNN-algorithms

图神经网络相关算法详述及实现
https://github.com/wangyouze/GNN-algorithms

Last synced: about 1 month ago
JSON representation

图神经网络相关算法详述及实现

• Host: GitHub
• URL: https://github.com/wangyouze/GNN-algorithms
• Owner: wangyouze
• Created: 2020-07-03T05:03:46.000Z (over 4 years ago)
• Default Branch: master
• Last Pushed: 2020-11-25T10:28:14.000Z (about 4 years ago)
• Last Synced: 2024-08-03T15:10:53.163Z (5 months ago)
• Size: 2.21 MB
• Stars: 805
• Watchers: 10
• Forks: 140
• Open Issues: 1
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

• awesome-machine-learning-resources - **[Tutorial - algorithms?style=social) (Table of Contents)

README

        
# GNN-algorithms

图神经网络相关算法详述及实现教程。

受到**pytorch_geometric**的启发，我们开发了基于Tensorflow的GNN库:[tf_geometric](https://github.com/CrawlScript/tf_geometric)，其中集成了高效且对科研工作者友好的GNN模型。GNN-algorighms则是基于tf_geometric对近几年如火如荼的图神经模型进行详述以及手把手教大家实现GNN模型的教程。

### 目录

***

1. [图卷积网络的前世今生](https://github.com/wangyouze/GNN-algorithms/tree/master/GCN%E7%9A%84%E5%89%8D%E4%B8%96%E4%BB%8A%E7%94%9F)

2. [切比雪夫显神威—ChebyNet](https://github.com/wangyouze/GNN-algorithms/tree/master/ChebyNet-%E5%88%87%E6%AF%94%E9%9B%AA%E5%A4%AB%E5%A4%9A%E9%A1%B9%E5%BC%8F%E8%BF%91%E4%BC%BC%E5%9B%BE%E5%8D%B7%E7%A7%AF%E6%A0%B8)

3. [删繁就简GCN—SGC](https://github.com/wangyouze/GNN-algorithms/tree/master/SGC-%E7%AE%80%E5%8C%96GCN)

4. [多核卷积拓扑图—TAGCN](https://github.com/wangyouze/GNN-algorithms/tree/master/TAGCN-%E9%83%A8%E5%88%86%E8%BF%98%E5%8E%9FGCN%E5%AF%B9%E5%8D%B7%E7%A7%AF%E6%A0%B8%E7%9A%84%E7%AE%80%E5%8C%96)

5. [归纳学习采样聚合—GraphSAGE](https://github.com/wangyouze/GNN-algorithms/tree/master/GraphSAGE-%E5%AD%A6%E4%B9%A0%E8%81%9A%E5%90%88%E5%87%BD%E6%95%B0)

6. [多头注意聚合信息—GAT](https://github.com/wangyouze/GNN-algorithms/tree/master/GAT-%E6%B3%A8%E6%84%8F%E5%8A%9B%E6%9C%BA%E5%88%B6%E5%9C%A8%E5%9B%BE%E4%B8%8A%E7%9A%84%E5%BA%94%E7%94%A8)

7. [How Powerful Are Graph Neural Networks—GIN](https://github.com/wangyouze/GNN-algorithms/tree/master/ChebyNet-%E5%88%87%E6%AF%94%E9%9B%AA%E5%A4%AB%E5%A4%9A%E9%A1%B9%E5%BC%8F%E8%BF%91%E4%BC%BC%E5%9B%BE%E5%8D%B7%E7%A7%AF%E6%A0%B8)

8. [无监督学习图表示—GAE](https://github.com/CrawlScript/TensorFlow-GAE-Tutorial)

***

本人才疏学浅，如教程有任何不妥或者错误之处，欢迎扫描下方的二维码加群或者开issue讨论。同时本群也欢迎志同道合之士加群共同探讨图神经网络。AI恒久远，GNN永流传。（由于GNN-algorithms交流群人数已经超过200人，只能通过邀请进群，有意者请扫码加我微信，邀你进群）