mlsanityData to 14 Oct 2026

Over-Squashing in Graph Neural Networks: A Comprehensive survey

arXiv 2308.15568 ↗First posted 29 Aug 2023cs.AIcited by 23

Not on the map. Why?

Abstract (arXiv)

Graph Neural Networks (GNNs) revolutionize machine learning for graph-structured data, effectively capturing complex relationships. They disseminate information through interconnected nodes, but long-range interactions face challenges known as "over-squashing". This survey delves into the challenge of over-squashing in Graph Neural Networks (GNNs), where long-range information dissemination is hindered, impacting tasks reliant on intricate long-distance interactions. It comprehensively explores the causes, consequences, and mitigation strategies for over-squashing. Various methodologies are reviewed, including graph rewiring, novel normalization, spectral analysis, and curvature-based strategies, with a focus on their trade-offs and effectiveness. The survey also discusses the interplay between over-squashing and other GNN limitations, such as over-smoothing, and provides a taxonomy of models designed to address these issues in node and graph-level tasks. Benchmark datasets for performance evaluation are also detailed, making this survey a valuable resource for researchers and practitioners in the GNN field.

Key facts. Cited by 23 papers in the map (data through 14 Oct 2026). Builds on 65 of its 116 references that are in the map. First posted on arXiv 29 Aug 2023.

Builds on

65 of 116 references.

References · 65

  1. 2017Inductive Representation Learning on Large Graphscited by 6,320
  2. 2018How Powerful are Graph Neural Networks?cited by 4,393
  3. 2017Neural Message Passing for Quantum Chemistrycited by 3,487
  4. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,919
  5. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,089
  6. 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,576
  7. 2019Simplifying Graph Convolutional Networkscited by 1,477
  8. 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,102
  9. 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 993
  10. 2020Geom-GCN: Geometric Graph Convolutional Networkscited by 826
  11. 2018Hierarchical Graph Representation Learning with Differentiable Poolingcited by 787
  12. 2020TUDataset: A collection of benchmark datasets for learning with graphscited by 728
38 more
  1. 2022Recipe for a General, Powerful, Scalable Graph Transformercited by 713
  2. 2019DropEdge: Towards Deep Graph Convolutional Networks on Node Classificationcited by 680
  3. 2020On the Bottleneck of Graph Neural Networks and its Practical Implicationscited by 631
  4. 2019Multi-scale Attributed Node Embeddingcited by 548
  5. 2019Graph Transformer Networkscited by 523
  6. 2021Understanding over-squashing and bottlenecks on graphs via curvaturecited by 478
  7. 2021Rethinking Graph Transformers with Spectral Attentioncited by 473
  8. 2019Diffusion Improves Graph Learningcited by 414
  9. 2020Explainability in Graph Neural Networks: A Taxonomic Surveycited by 384
  10. 2023A critical look at the evaluation of GNNs under heterophily: Are we really making progress?cited by 343
  11. 2023A Survey on Oversmoothing in Graph Neural Networkscited by 247
  12. 2022Representing Long-Range Context for Graph Neural Networks with Global Attentioncited by 195
  13. 2020Scaling Graph Neural Networks with Approximate PageRankcited by 174
  14. 2023On Over-Squashing in Message Passing Neural Networks: The Impact of Width, Depth, and Topologycited by 166
  15. 2020Directional Graph Networkscited by 133
  16. 2022Graph-Coupled Oscillator Networkscited by 124
  17. 2020Towards Deeper Graph Neural Networks with Differentiable Group Normalizationcited by 114
  18. 2020A Survey on The Expressive Power of Graph Neural Networkscited by 111
  19. 2022FoSR: First-order spectral rewiring for addressing oversquashing in GNNscited by 105
  20. 2022Revisiting Over-smoothing and Over-squashing Using Ollivier-Ricci Curvaturecited by 98
  21. 2023Understanding Oversquashing in GNNs through the Lens of Effective Resistancecited by 97
  22. 2022A Generalization of ViT/MLP-Mixer to Graphscited by 93
  23. 2021Knowledge Graph Reasoning with Relational Digraphcited by 92
  24. 2020Differentiable Graph Module (DGM) for Graph Convolutional Networkscited by 86
  25. 2019Graph Transformer for Graph-to-Sequence Learningcited by 82
  26. 2023DRew: Dynamically Rewired Message Passing with Delaycited by 82
  27. 2022DiffWire: Inductive Graph Rewiring via the Lov'asz Boundcited by 79
  28. 2022Expander Graph Propagationcited by 75
  29. 2023On the Connection Between MPNN and Graph Transformercited by 61
  30. 2022Anti-Symmetric DGN: a stable architecture for Deep Graph Networkscited by 60
  31. 2022A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Perspectivecited by 56
  32. 2020Multi-hop Attention Graph Neural Networkcited by 53
  33. 2021Equivariant Graph Neural Networks for 3D Macromolecular Structurecited by 53
  34. 2022Oversquashing in GNNs through the lens of information contraction and graph expansioncited by 53
  35. 2023How does over-squashing affect the power of GNNs?cited by 53
  36. 2022A Non-Asymptotic Analysis of Oversmoothing in Graph Neural Networkscited by 49
  37. 2022Message passing all the way upcited by 47
  38. 2020Advanced Graph and Sequence Neural Networks for Molecular Property Prediction and Drug Discoverycited by 46

50 most cited of 65 All 65 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 5; 2025: 7; 2026: 10.

23 papers.

Sort:

By area:

  1. 2023Exposition on over-squashing problem on GNNs: Current Methods, Benchmarks and Challengescited by 22
  2. 2025Oversmoothing, Oversquashing, Heterophily, Long-Range, and more: Demystifying Common Beliefs in Graph Machine Learningcited by 19
  3. 2025DeepGate4: Efficient and Effective Representation Learning for Circuit Design at Scalecited by 12
  4. 2024Graph Rewiring in GNNs to Mitigate Over-Squashing and Over-Smoothing: A Surveycited by 8
  5. 2024Foundations and Frontiers of Graph Learning Theorycited by 3
  6. 2025Refined Causal Graph Structure Learning via Curvature for Brain Disease Classificationcited by 2
  7. 2025Efficient Curvature-aware Graph Networkcited by 2
  8. 2026Position: Don't be Afraid of Over-Smoothing And Over-Squashingcited by 2
  9. 2024GEN: A Practical Alternative to Graph Transformers for Long-Range Graph Modelingcited by 0
  10. 2024Message Detouring: A Simple Yet Effective Cycle Representation for Expressive Graph Learningcited by 0
  11. 2024Introduction to Graph Neural Networks for Machine Learning Engineerscited by 0
  12. 2025A Remedy for Over-Squashing in Graph Learning via Forman-Ricci Curvature based Graph-to-Hypergraph Structural Liftingcited by 0
11 more
  1. 2025On The Expressive Power of GNN Derivativescited by 0
  2. 2025Learning to Solve Resource-Constrained Project Scheduling Problems with Duration Uncertainty using Graph Neural Networkscited by 0
  3. 2026Approximate Subgraph Matching with Neural Graph Representations and Reinforcement Learningcited by 0
  4. 2026k-Maximum Inner Product Attention for Graph Transformers and the Expressive Power of GraphGPScited by 0
  5. 2026Graph Rewiring in GNNs to Mitigate Over-Squashing and Over-Smoothing: A Surveycited by 0
  6. 2026Geometrical fairness in graph neural networkscited by 0
  7. 2026LEED: Local Embedding Evolution Distance for over-smoothing estimation and virtual node selection in GNNcited by 0
  8. 2026Pair-Centric Graph Rewiring for Over-Squashing via Optimal Transport-Guided Communication Alignmentcited by 0
  9. 2026Graph Machine Learning: An Opportunity for Power Systemscited by 0
  10. 2026Omega-N: Interpretable Structural Node Descriptors and Their Applicability Domaincited by 0
  11. 2026Finite-Time Node Separation in Recurrent Graph Neural Networks with Persistent Gaussian Perturbationscited by 0