图卷积神经网络

1. 理论篇

1. 原理：http://xtf615.com/2019/02/24/gcn/
2. 论文：

综述类：

1. HOW POWERFUL ARE GRAPH NEURAL NETWORKS?
2. Bridging the Gap between Spatial and Spectral Domains: A Survey on Graph Neural Networks

研究类：

1. 第一代GCN：Spectral Networks and Locally Connected Networks on Graphs
2. 第二代GCN：Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
3. 第三代GCN：Semi-Supervised Classification with Graph Convolutional Networks

2. 模型篇

1. 论文：

综述类：

1. Graph Neural Networks: A Review of Methods and Applications
2. A Comprehensive Survey on Graph Neural Networks

研究类：

1. SimGNN: A Neural Network Approach to Fast Graph Similarity Computation
   （通过GNN求两个图的相似度）

2. Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting

3. 有关gnn的论文检索

https://github.com/thunlp/GNNPapers
https://github.com/ChandlerBang/awesome-self-supervised-gnn