Home

Awesome

awesome-deep-gnn

contributing-image

Papers about developing deep Graph Neural Networks (GNNs). Investigations about over-smoothing and over-squashing problem in GNNs are also included here.

Please feel free to submit a pull request if you want to add good papers.

<!-- ## Literature [sorted in reverse chronological order]-->

Most Influential Papers

Selected by CogDL

  1. [ICML 2018] Representation Learning on Graphs with Jumping Knowledge Networks [Paper]
  2. [AAAI 2018] Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning [Paper]
  3. [ICLR 2019] Predict then Propagate: Graph Neural Networks meet Personalized PageRank [Paper][Code]
  4. [ICCV 2019] DeepGCNs: Can GCNs Go as Deep as CNNs? [Paper][Code(Pytorch)][Code(TensorFlow)]
  5. [NeurIPS 2019] Layer-Dependent Importance Sampling for Training Deep and Large Graph Convolutional Networks. [Paper][Code]
  6. [arXiv 2020] DeeperGCN: All You Need to Train Deeper GCNs [Paper][Code]
  7. [ICLR 2020] PairNorm: Tackling Oversmoothing in GNNs [Paper][Code]
  8. [ICLR 2020] DropEdge: Towards Deep Graph Convolutional Networks on Node Classification [Paper][Code]
  9. [ICML 2020] Simple and Deep Graph Convolutional Networks [Paper][Code]
  10. [KDD 2020] Towards Deeper Graph Neural Networks [Paper][Code]

2022

2021

2020

Before 2020