# GNN图神经网络综述

## 图神经网络综述

* [返回顶层目录](https://luweikxy.gitbook.io/machine-learning-notes/graph-neural-networks/pages/-LpO5vE88qYwjk5WM_Qf#目录)
* [返回上层目录](/machine-learning-notes/graph-neural-networks.md)

## 参考资料

### 概述

[图神经网络综述：模型与应用](https://mp.weixin.qq.com/s/DIdJb_vG8_zLdp_t56jLXQ)

[一文带你入门图神经网络基础、DeepWalk及GraphSage](https://www.atyun.com/37085.html)

[【KDD2019】清华大学《图神经网络-算法、理论和应用》教程](https://mp.weixin.qq.com/s/rgcDlFA1_Qbu8xRH7WZrtA)

[图论、图算法与图学习](https://mp.weixin.qq.com/s/2U0shbDbkpEm0R_iGQ3K7Q)

[图深度学习资源汇总](https://mp.weixin.qq.com/s/sRzLb1NSzzKittcYGJCR5A)

[图神经网络GNN最新理论进展和应用探索，附报告下载](https://mp.weixin.qq.com/s/JvtrGa0YiUmR6UA5wBQ-pQ)

[深度学习时代的图模型，清华发文综述图网络](https://mp.weixin.qq.com/s/WW-URKk-fNct9sC4bJ22eg)

[图神经网络综述：模型与应用](https://mp.weixin.qq.com/s/DIdJb_vG8_zLdp_t56jLXQ)

[图神经网络概述第三弹：来自IEEE Fellow的GNN综述](https://zhuanlan.zhihu.com/p/54241746)

[CNN已老，GNN来了！清华大学孙茂松组一文综述GNN](https://mp.weixin.qq.com/s/h4jQWJlQV2Ew3SpuF8k5Hw)

[【图深度学习时代降临】清华朱文武组一文综述GraphDL五类模型](https://mp.weixin.qq.com/s/eelcT5x_kWC0dDt0_Ph4qg)

[图神经网络概述第三弹：来自IEEE Fellow的GNN综述](https://mp.weixin.qq.com/s/0rs8Wur7Iv6jSpFz5C-KNg)

[深度学习局限何在？图网络的出现并非偶然](https://mp.weixin.qq.com/s/K-VB_7lhYA_2vvJ3pLauqQ)

[AAAI 2019 论文解读：卷积神经网络继续进步](https://zhuanlan.zhihu.com/p/56194480?utm_source=wechat_session\&utm_medium=social\&utm_oi=903049909593317376\&app=zhihulite\&utm_campaign=lite_share\&invite_code=1JRJFP\&sign=MTU0OTEwOTc1NzQ2Mw%3D%3D\&from=timeline\&s_s_i=vnDd7RLbXtJHJyl5NkaJZPBYsI%2FSEJzKq9IHNrfTh4U%3D\&s_r=1)

[近期必读的6篇【图神经网络的推荐（GNN+R）】相关论文和代码（WWW、SIGIR、WSDM）](https://mp.weixin.qq.com/s/vULrKf7wQeQYtnfsoQXqAw)

[Google图挖掘团队最新博客《图表示学习中的创新》，附PDF下载](https://mp.weixin.qq.com/s/_8K0s9WceJ-xlRViHhz2Zw)

[近期必读的12篇KDD 2019【图神经网络（GNN）】相关论文](https://mp.weixin.qq.com/s/r1K2Ry_GR1RN0frcr_HzLA)

[神经网络图的简介（基本概念，DeepWalk以及GraphSage算法）](https://ai.yanxishe.com/page/TextTranslation/1485?from=timeline)

[认知推理：从图表示学习和图神经网络的最新理论看AI的未来](https://zhuanlan.zhihu.com/p/131508787)

### 实践

[PyTorch & PyTorch Geometric图神经网络(GNN)实战](https://mp.weixin.qq.com/s/_aIPVnJfTWMkCbh4h6MAEA)

[解决关系推理，从图网络入手！DeepMind图网络库开源了！](https://zhuanlan.zhihu.com/p/47209785?utm_source=wechat_session\&utm_medium=social\&utm_oi=903049909593317376\&app=zhihulite\&utm_campaign=lite_share\&invite_code=1JRJFP\&sign=MTU0OTMyODMwNjI3NA%3D%3D\&from=timeline\&s_s_i=vnDd7RLbXtJHJyl5NkaJZPBYsI%2FSEJzKq9IHNrfTh4U%3D\&s_r=1)

[学界 | 北大、微软提出NGra：高效大规模图神经网络计算](https://mp.weixin.qq.com/s/EiHByVjVCPQngzp3JYMeEA)

[Euler 今日问世！国内首个工业级的图深度学习开源框架，阿里妈妈造](https://mp.weixin.qq.com/s/CXFgrLbjgCno0H74rtTSuQ)

[新的PyTorch图神经网络库强势来袭，GitHub 2200星](https://mp.weixin.qq.com/s/5tGA8DwAQ-wxm96xJkZfFA)

[图卷积网络到底怎么做，这是一份极简的Numpy实现](https://www.jiqizhixin.com/articles/2019-02-20-12)

### 知识

[GCN作者Thomas Kipf 最新Talk：利用图神经网络进行无监督学习](https://mp.weixin.qq.com/s/PxNGJ0hcmCo-2zvWD-rfug)

[GATs:图神经网络中的注意力机制](https://zhuanlan.zhihu.com/p/66812926?utm_source=wechat_session\&utm_medium=social\&utm_oi=903049909593317376)

### 论文

[Github上的图神经网络必读论文和最新进展列表20190521](https://mp.weixin.qq.com/s/M_mHgbzWsooUcWtdpP_OCQ)

[【ICLR 2019论文】互信息最大化的无监督图神经网络Deep Graph Infomax](https://mp.weixin.qq.com/s/IC-bfSQp-ctXvmLCtB2-4Q)

《Graph Neural Network多强大？》阅读笔记 知乎 陈乐天

研究者

宋国洁：

[FYI：SMP 2018 会议报告下载页面推荐！](https://mp.weixin.qq.com/s/GRNt2ZjSmR3uV6yhbgT_sA)

[社交网络和数据挖掘](http://www.mooc.ai/course/307)


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://luweikxy.gitbook.io/machine-learning-notes/graph-neural-networks/graph-neural-networks-review.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.