mlsanityData to 7 Oct 2026

Simple and Deep Graph Convolutional Networks

arXiv 2007.02133 ↗First posted 4 Jul 2020cs.LG stat.MLcited by 857

Not on the map. Why?

Abstract (arXiv)

Graph convolutional networks (GCNs) are a powerful deep learning approach for graph-structured data. Recently, GCNs and subsequent variants have shown superior performance in various application areas on real-world datasets. Despite their success, most of the current GCN models are shallow, due to the em over-smoothing problem. In this paper, we study the problem of designing and analyzing deep graph convolutional networks. We propose the GCNII, an extension of the vanilla GCN model with two simple yet effective techniques: em Initial residual and em Identity mapping. We provide theoretical and empirical evidence that the two techniques effectively relieves the problem of over-smoothing. Our experiments show that the deep GCNII model outperforms the state-of-the-art methods on various semi- and full-supervised tasks. Code is available at https://github.com/chennnM/GCNII .

Key facts. Cited by 857 papers in the map (data through 7 Oct 2026). First posted on arXiv 4 Jul 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 114; 2022: 161; 2023: 187; 2024: 181; 2025: 137; 2026: 77.

857 papers.

Sort:

By area:

  1. 2021Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methodscited by 309
  2. 2022Long Range Graph Benchmarkcited by 258
  3. 2023A Survey on Oversmoothing in Graph Neural Networkscited by 246
  4. 2023Language is All a Graph Needscited by 219
  5. 2022Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNscited by 208
  6. 2021Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networkscited by 182
  7. 2021Is Homophily a Necessity for Graph Neural Networks?cited by 182
  8. 2022Finding Global Homophily in Graph Neural Networks When Meeting Heterophilycited by 179
  9. 2022Graph Neural Networks for Graphs with Heterophily: A Surveycited by 175
  10. 2021Training Graph Neural Networks with 1000 Layerscited by 169
  11. 2022Revisiting Heterophily For Graph Neural Networkscited by 169
  12. 2022Handling Distribution Shifts on Graphs: An Invariance Perspectivecited by 163
38 more
  1. 2021Graph-less Neural Networks: Teaching Old MLPs New Tricks via Distillationcited by 151
  2. 2022NAGphormer: A Tokenized Graph Transformer for Node Classification in Large Graphscited by 137
  3. 2021Interpreting and Unifying Graph Neural Networks with An Optimization Frameworkcited by 131
  4. 2021UniGNN: a Unified Framework for Graph and Hypergraph Neural Networkscited by 127
  5. 2022Graph-Coupled Oscillator Networkscited by 123
  6. 2021Learning Graph Embeddings for Compositional Zero-shot Learningcited by 112
  7. 2023GraphText: Graph Reasoning in Text Spacecited by 110
  8. 2021PDE-GCN: Novel Architectures for Graph Neural Networks Motivated by Partial Differential Equationscited by 106
  9. 2022Not too little, not too much: a theoretical analysis of graph (over)smoothingcited by 106
  10. 2021MMGCN: Multimodal Fusion via Deep Graph Convolution Network for Emotion Recognition in Conversationcited by 99
  11. 2021Dirichlet Energy Constrained Learning for Deep Graph Neural Networkscited by 97
  12. 2022Decoupling the Depth and Scope of Graph Neural Networkscited by 94
  13. 2021GNNAutoScale: Scalable and Expressive Graph Neural Networks via Historical Embeddingscited by 90
  14. 2022Convolutional Neural Networks on Graphs with Chebyshev Approximation, Revisitedcited by 87
  15. 2021GraphEBM: Molecular Graph Generation with Energy-Based Modelscited by 85
  16. 2023DIFFormer: Scalable (Graph) Transformers Induced by Energy Constrained Diffusioncited by 85
  17. 2021GBK-GNN: Gated Bi-Kernel Graph Neural Networks for Modeling Both Homophily and Heterophilycited by 84
  18. 2022Debiasing Graph Neural Networks via Learning Disentangled Causal Substructurecited by 83
  19. 2023Where Did the Gap Go? Reassessing the Long-Range Graph Benchmarkcited by 83
  20. 2024Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classificationcited by 83
  21. 2021Is Heterophily A Real Nightmare For Graph Neural Networks To Do Node Classification?cited by 82
  22. 2022Graph Attention Multi-Layer Perceptroncited by 82
  23. 2021New Benchmarks for Learning on Non-Homophilous Graphscited by 81
  24. 2021Scaling Up Graph Neural Networks Via Graph Coarseningcited by 80
  25. 2022Neo-GNNs: Neighborhood Overlap-aware Graph Neural Networks for Link Predictioncited by 78
  26. 2022Fairness in Graph Mining: A Surveycited by 76
  27. 2021Towards Self-Explainable Graph Neural Networkcited by 75
  28. 2024OpenGraph: Towards Open Graph Foundation Modelscited by 75
  29. 2023A Comprehensive Survey on Deep Graph Representation Learningcited by 72
  30. 2021Extract the Knowledge of Graph Neural Networks and Go Beyond it: An Effective Knowledge Distillation Frameworkcited by 69
  31. 2023Ordered GNN: Ordering Message Passing to Deal with Heterophily and Over-smoothingcited by 67
  32. 2022A Survey on Graph Representation Learning Methodscited by 66
  33. 2022Sheaf Neural Networks with Connection Laplacianscited by 64
  34. 2024Polynormer: Polynomial-Expressive Graph Transformer in Linear Timecited by 64
  35. 2022Towards Robust Graph Neural Networks for Noisy Graphs with Sparse Labelscited by 63
  36. 2022Structural Entropy Guided Graph Hierarchical Poolingcited by 62
  37. 2022Improving Fairness in Graph Neural Networks via Mitigating Sensitive Attribute Leakagecited by 61
  38. 2021Graph Neural Networks Inspired by Classical Iterative Algorithmscited by 60

50 most cited of 857 All 857 (JSON)