TOP 100值得读的图神经网络----架构_discriminative graph convolutional networks for se

Top100值得一读的图神经网络 (qq.com)https://mp.weixin.qq.com/s?__biz=MzIyNDY5NjEzNQ==&mid=2247491631&idx=1&sn=dfa36e829a84494c99bb2d4f755717d6&chksm=e809a207df7e2b1117578afc86569fa29ee62eb883fd35428888c0cc0be750faa5ef091f9092&mpshare=1&scene=23&srcid=1026NUThrKm2Vioj874F3gqS&sharer_sharetime=1635227630762&sharer_shareid=80f244b289da8c80b67c915b10efd0a8#rd清华大学的Top 100 GNN papers，其中分了十个方向，每个方向10篇

本文是对架构方向10篇的阅读笔记：

1. Semi-Supervised Classification with Graph Convolutional Networks. Thomas N. Kipf, Max Welling. NeuIPS'17.
2. Graph Attention Networks. Petar Veličković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Liò, Yoshua Bengio. ICLR'18.
3. Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering. NeuIPS'16.
4. Predict then Propagate: Graph Neural Networks meet Personalized PageRank. Johannes Klicpera, Aleksandar Bojchevski, Stephan Günnemann. ICLR'19.
5. Gated Graph Sequence Neural Networks. Li, Yujia N and Tarlow, Daniel and Brockschmidt, Marc and Zemel, Richard. ICLR'16.
6. Inductive Representation Learning on Large Graphs. William L. Hamilton, Rex Ying, Jure Leskovec. NeuIPS'17.
7. Deep Graph Infomax. Petar Veličković, William Fedus, William L. Hamilton, Pietro Liò, Yoshua Bengio, R Devon Hjelm. ICLR'19.
8. Representation Learning on Graphs with Jumping Knowledge Networks. Keyulu Xu, Chengtao Li, Yonglong Tian, Tomohiro Sonobe, Ken-ichi Kawarabayashi, Stefanie Jegelka. ICML'18.
9. DeepGCNs: Can GCNs Go as Deep as CNNs?. Guohao Li, Matthias Müller, Ali Thabet, Bernard Ghanem. ICCV'19.
10. DropEdge: Towards Deep Graph Convolutional Networks on Node Classification. Yu Rong, Wenbing Huang, Tingyang Xu, Junzhou Huang. ICLR'20

目录

一、GCN 基于图卷积网络的半监督分类  SEMI-SUPERVISED CLASSIFICATION WITH GRAPH CONVOLUTIONAL NETWORKS

二、GAT 图注意力网络 Graph Attention Networks

三、具有快速局部谱滤波的图上的卷积神经网络 Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering

四、预测后传播：图神经网络满足个性化PageRank PREDICT THEN PROPAGATE: GRAPH NEURAL NETWORKS MEET PERSONALIZED PAGERANK

五、门控图序列神经网络 GATED GRAPH SEQUENCE NEURAL NETWORKS

六、GraphSAGE大型图的归纳表示学习 Inductive Representation Learning on Large Graphs

七、DGI DEEP GRAPH INFOMAX          

八、JK Representation Learning on Graphs with Jumping Knowledge Networks         

九、DeepGCNs: Can GCNs Go as Deep as CNNs?           

十、DROPEDGE: TOWARDS DEEP GRAPH CONVOLUTIONAL NETWORKS ON NODE CLASSIFICATION

             

---

一、GCN 基于图卷积网络的半监督分类  SEMI-SUPERVISED CLASSIFICATION WITH GRAPH CONVOLUTIONAL NETWORKS