图卷积入门流程

图卷积入门流程

提示：文章写完后，目录可以自动生成，如何生成可参考右边的帮助文档

---

前言

提示：这里可以添加本文要记录的大概内容：

图卷积（GCN）学习该如何入门？？按照以下学习步骤

---

提示：以下是本篇文章正文内容，下面案例可供参考

一、CNN卷积神经网络是什么？

在学习图卷积之前需要先了解基础的卷积神经网络

1.学习blog

如下（按步骤学习）：
①CNN笔记：通俗理解卷积神经网络
https://blog.csdn.net/v_JULY_v/article/details/51812459?spm=1001.2014.3001.5506
②三万字硬核详解：卷积神经网络CNN（原理详解 + 项目实战 ）https://blog.csdn.net/shinuone/article/details/127289512?spm=1001.2014.3001.5506
③Pytorch nn.Linear的基本用法与原理详解https://blog.csdn.net/zhaohongfei_358/article/details/122797190?spm=1001.2014.3001.5506
④准确率Accuracy与损失函数Loss的关系
https://blog.csdn.net/u014421797/article/details/104689384?spm=1001.2014.3001.5506
⑤Dropout的深入理解https://blog.csdn.net/weixin_42475060/article/details/128862411?spm=1001.2014.3001.5506
⑥三分钟认知Softmax和Sigmoid的详细区别
https://blog.csdn.net/weixin_47872288/article/details/127301342?spm=1001.2014.3001.5506
。。。

二、GCN图卷积网络是什么？

1.学习blog

如下（按步骤学习）：
①图卷积网络 GCN Graph Convolutional Network（谱域GCN）的理解和详细推导
https://blog.csdn.net/yyl424525/article/details/100058264/?ops_request_misc=&request_id=&biz_id=102&utm_term=%E4%B8%A4%E4%B8%AA%E6%9C%80%E5%B8%B8%E8%A7%81%E7%9A%84GCNs%E6%93%8D%E4%BD%9C%20%E7%89%B9%E5%BE%81%E5%8F%98%E5%8C%96&utm_medium=distribute.pc_search_result.none-task-blog-2_allsobaiduweb~default-5-100058264.142^v100pc_search_result_base7&spm=1018.2226.3001.4187
②如何理解 Graph Convolutional Network（GCN）？https://www.zhihu.com/question/54504471/answer/332657604
③精通GCN全攻略
https://www.zhihu.com/column/c_1131513793020334080
④基于空间域的图卷积GCNs（ConvGNNs）
https://blog.csdn.net/yyl424525/article/details/103172141?ops_request_misc=%257B%2522request%255Fid%2522%253A%2522172351829316800188583460%2522%252C%2522scm%2522%253A%252220140713.130102334.pc%255Fall.%2522%257D&request_id=172351829316800188583460&biz_id=0&utm_medium=distribute.pc_search_result.none-task-blog-2_allfirst_rank_ecpm_v1~rank_v31_ecpm-8-103172141-null-null.142^v100pc_search_result_base7&utm_term=%E4%B8%A4%E4%B8%AA%E6%9C%80%E5%B8%B8%E8%A7%81%E7%9A%84GCNs%E6%93%8D%E4%BD%9C%20%E7%89%B9%E5%BE%81%E5%8F%98%E5%8C%96&spm=1018.2226.3001.4187
。。。

2.学习paper

如下（学完上面前三篇blog后，结合下面文章学习）：
①The emerging graph neural networks for intelligent fault diagnostics and prognostics: A guideline and a benchmark study. MSSP. 2022
②Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning. AAAI. 2018
论文解读https://www.cnblogs.com/BlairGrowing/p/16224089.html
作者主页https://liqimai.github.io/publications/
③Simple and Deep Graph Convolutional Networks. ICML. 2020
。。。

总结

提示：这里对文章进行总结：
例如：以上就是今天要讲的内容，本文仅仅简单介绍了图卷积的入门。