mlsanityData to 7 Oct 2026

Simplifying Graph Convolutional Networks

arXiv 1902.07153 ↗First posted 19 Feb 2019cs.LG stat.MLcited by 1,470

Not on the map. Why?

Abstract (arXiv)

Graph Convolutional Networks (GCNs) and their variants have experienced significant attention and have become the de facto methods for learning graph representations. GCNs derive inspiration primarily from recent deep learning approaches, and as a result, may inherit unnecessary complexity and redundant computation. In this paper, we reduce this excess complexity through successively removing nonlinearities and collapsing weight matrices between consecutive layers. We theoretically analyze the resulting linear model and show that it corresponds to a fixed low-pass filter followed by a linear classifier. Notably, our experimental evaluation demonstrates that these simplifications do not negatively impact accuracy in many downstream applications. Moreover, the resulting model scales to larger datasets, is naturally interpretable, and yields up to two orders of magnitude speedup over FastGCN.

Key facts. Cited by 1,470 papers in the map (data through 7 Oct 2026). First posted on arXiv 19 Feb 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 260; 2022: 294; 2023: 292; 2024: 322; 2025: 188; 2026: 114.

1,470 papers.

Sort:

By area:

  1. 2021How Attentive are Graph Attention Networks?cited by 818
  2. 2021Beyond Low-frequency Information in Graph Convolutional Networkscited by 361
  3. 2023A critical look at the evaluation of GNNs under heterophily: Are we really making progress?cited by 332
  4. 2021OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphscited by 328
  5. 2021Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methodscited by 309
  6. 2022A Survey of Machine Unlearningcited by 298
  7. 2021Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Predictioncited by 273
  8. 2021A Survey on Deep Semi-supervised Learningcited by 250
  9. 2023Language is All a Graph Needscited by 219
  10. 2022Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNscited by 208
  11. 2023NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classificationcited by 207
  12. 2021BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximationcited by 195
38 more
  1. 2022Rethinking Graph Neural Networks for Anomaly Detectioncited by 185
  2. 2021Large-Scale Representation Learning on Graphs via Bootstrappingcited by 184
  3. 2021Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networkscited by 182
  4. 2023MedCPT: Contrastive Pre-trained Transformers with Large-scale PubMed Search Logs for Zero-shot Biomedical Information Retrievalcited by 182
  5. 2024LLaGA: Large Language and Graph Assistantcited by 177
  6. 2021Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learningcited by 175
  7. 2022Graph Neural Networks for Graphs with Heterophily: A Surveycited by 175
  8. 2021The Values Encoded in Machine Learning Researchcited by 172
  9. 2021Training Graph Neural Networks with 1000 Layerscited by 169
  10. 2022How Powerful are Spectral Graph Neural Networkscited by 169
  11. 2022Revisiting Heterophily For Graph Neural Networkscited by 169
  12. 2022Handling Distribution Shifts on Graphs: An Invariance Perspectivecited by 163
  13. 2021From Stars to Subgraphs: Uplifting Any GNN with Local Structure Awarenesscited by 154
  14. 2021Graph-less Neural Networks: Teaching Old MLPs New Tricks via Distillationcited by 151
  15. 2021Graph Condensation for Graph Neural Networkscited by 150
  16. 2024MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformerscited by 140
  17. 2021Node Feature Extraction by Self-Supervised Multi-scale Neighborhood Predictioncited by 137
  18. 2022NAGphormer: A Tokenized Graph Transformer for Node Classification in Large Graphscited by 137
  19. 2022Anti-Oversmoothing in Deep Vision Transformers via the Fourier Domain Analysis: From Theory to Practicecited by 136
  20. 2022Data Augmentation for Deep Graph Learning: A Surveycited by 132
  21. 2021Interpreting and Unifying Graph Neural Networks with An Optimization Frameworkcited by 131
  22. 2023GraphMAE2: A Decoding-Enhanced Masked Self-Supervised Graph Learnercited by 131
  23. 2023SGFormer: Simplifying and Empowering Transformers for Large-Graph Representationscited by 131
  24. 2021You are AllSet: A Multiset Function Framework for Hypergraph Neural Networkscited by 124
  25. 2022Decoupled Dynamic Spatial-Temporal Graph Neural Network for Traffic Forecastingcited by 122
  26. 2021Advances and Challenges in Conversational Recommender Systems: A Surveycited by 118
  27. 2021Federated Graph Classification over Non-IID Graphscited by 113
  28. 2021Learning Graph Embeddings for Compositional Zero-shot Learningcited by 112
  29. 2023GraphText: Graph Reasoning in Text Spacecited by 110
  30. 2022Not too little, not too much: a theoretical analysis of graph (over)smoothingcited by 106
  31. 2021InfoGCL: Information-Aware Graph Contrastive Learningcited by 105
  32. 2021Learning Graph Structures with Transformer for Multivariate Time Series Anomaly Detection in IoTcited by 104
  33. 2023Specformer: Spectral Graph Neural Networks Meet Transformerscited by 102
  34. 2021Robustness of Graph Neural Networks at Scalecited by 100
  35. 2022Condensing Graphs via One-Step Gradient Matchingcited by 100
  36. 2021Dirichlet Energy Constrained Learning for Deep Graph Neural Networkscited by 97
  37. 2022Out-Of-Distribution Generalization on Graphs: A Surveycited by 97
  38. 2021Learning Intents behind Interactions with Knowledge Graph for Recommendationcited by 94

50 most cited of 1,470 All 1,470 (JSON)