mlsanityData to 7 Oct 2026

Geom-GCN: Geometric Graph Convolutional Networks

arXiv 2002.05287 ↗First posted 13 Feb 2020cs.LG cs.CV stat.MLcited by 821

Not on the map. Why?

Abstract (arXiv)

Message-passing neural networks (MPNNs) have been successfully applied to representation learning on graphs in a variety of real-world applications. However, two fundamental weaknesses of MPNNs' aggregators limit their ability to represent graph-structured data: losing the structural information of nodes in neighborhoods and lacking the ability to capture long-range dependencies in disassortative graphs. Few studies have noticed the weaknesses from different perspectives. From the observations on classical neural network and network geometry, we propose a novel geometric aggregation scheme for graph neural networks to overcome the two weaknesses. The behind basic idea is the aggregation on a graph can benefit from a continuous space underlying the graph. The proposed aggregation scheme is permutation-invariant and consists of three modules, node embedding, structural neighborhood, and bi-level aggregation. We also present an implementation of the scheme in graph convolutional networks, termed Geom-GCN (Geometric Graph Convolutional Networks), to perform transductive learning on graphs. Experimental results show the proposed Geom-GCN achieved state-of-the-art performance on a wide range of open datasets of graphs. Code is available at https://github.com/graphdml-uiuc-jlu/geom-gcn.

Key facts. Cited by 821 papers in the map (data through 7 Oct 2026). First posted on arXiv 13 Feb 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 87; 2022: 144; 2023: 149; 2024: 188; 2025: 153; 2026: 100.

821 papers.

Sort:

By area:

  1. 2021Understanding over-squashing and bottlenecks on graphs via curvaturecited by 471
  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. 2021Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methodscited by 309
  5. 2022Long Range Graph Benchmarkcited by 258
  6. 2023A Survey on Oversmoothing in Graph Neural Networkscited by 246
  7. 2023Language is All a Graph Needscited by 219
  8. 2022Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNscited by 208
  9. 2023NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classificationcited by 207
  10. 2021BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximationcited by 195
  11. 2021Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networkscited by 182
  12. 2021Is Homophily a Necessity for Graph Neural Networks?cited by 182
38 more
  1. 2022Finding Global Homophily in Graph Neural Networks When Meeting Heterophilycited by 179
  2. 2022Graph Neural Networks for Graphs with Heterophily: A Surveycited by 175
  3. 2022How Powerful are Spectral Graph Neural Networkscited by 169
  4. 2022Revisiting Heterophily For Graph Neural Networkscited by 169
  5. 2021Node Feature Extraction by Self-Supervised Multi-scale Neighborhood Predictioncited by 137
  6. 2022Graph-Coupled Oscillator Networkscited by 123
  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. 2021MagNet: A Neural Network for Directed Graphscited by 104
  10. 2022How to Find Your Friendly Neighborhood: Graph Attention Design with Self-Supervisioncited by 102
  11. 2023Specformer: Spectral Graph Neural Networks Meet Transformerscited by 102
  12. 2022Revisiting Over-smoothing and Over-squashing Using Ollivier-Ricci Curvaturecited by 96
  13. 2021Breaking the Limit of Graph Neural Networks by Improving the Assortativity of Graphs with Local Mixing Patternscited by 95
  14. 2021Parameter Prediction for Unseen Deep Architecturescited by 89
  15. 2023Edge Directionality Improves Learning on Heterophilic Graphscited by 88
  16. 2022Convolutional Neural Networks on Graphs with Chebyshev Approximation, Revisitedcited by 87
  17. 2021GBK-GNN: Gated Bi-Kernel Graph Neural Networks for Modeling Both Homophily and Heterophilycited by 84
  18. 2024All in One and One for All: A Simple yet Effective Method towards Cross-domain Graph Pretrainingcited by 84
  19. 2024Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classificationcited by 83
  20. 2021Is Heterophily A Real Nightmare For Graph Neural Networks To Do Node Classification?cited by 82
  21. 2024GFT: Graph Foundation Model with Transferable Tree Vocabularycited by 82
  22. 2021New Benchmarks for Learning on Non-Homophilous Graphscited by 81
  23. 2023Attending to Graph Transformerscited by 81
  24. 2022Hierarchical Graph Transformer with Adaptive Node Samplingcited by 72
  25. 2023Ordered GNN: Ordering Message Passing to Deal with Heterophily and Over-smoothingcited by 67
  26. 2022A Survey on Graph Representation Learning Methodscited by 66
  27. 2022Sheaf Neural Networks with Connection Laplacianscited by 64
  28. 2022On the Trade-off between Over-smoothing and Over-squashing in Deep Graph Neural Networkscited by 63
  29. 2023Graph Mixture of Experts: Learning on Large-Scale Graphs with Explicit Diversity Modelingcited by 63
  30. 2022Understanding and Improving Graph Injection Attack by Promoting Unnoticeabilitycited by 62
  31. 2025SAMGPT: Text-free Graph Foundation Model for Multi-domain Pre-training and Cross-domain Adaptationcited by 61
  32. 2021Graph Neural Networks Inspired by Classical Iterative Algorithmscited by 60
  33. 2022Characterizing Graph Datasets for Node Classification: Homophily-Heterophily Dichotomy and Beyondcited by 60
  34. 2022Understanding convolution on graphs via energiescited by 58
  35. 2022Anti-Symmetric DGN: a stable architecture for Deep Graph Networkscited by 58
  36. 2021Cold Brew: Distilling Graph Node Representations with Incomplete or Missing Neighborhoodscited by 57
  37. 2022GraphFramEx: Towards Systematic Evaluation of Explainability Methods for Graph Neural Networkscited by 57
  38. 2022Beyond Smoothing: Unsupervised Graph Representation Learning with Edge Heterophily Discriminatingcited by 57

50 most cited of 821 All 821 (JSON)