mlsanityData to 14 Oct 2026

Leave Graphs Alone: Addressing Over-Squashing without Rewiring

arXiv 2212.06538 ↗First posted 13 Dec 2022cs.LGcited by 14

Not on the map. Why?

Abstract (arXiv)

Recent works have investigated the role of graph bottlenecks in preventing long-range information propagation in message-passing graph neural networks, causing the so-called `over-squashing' phenomenon. As a remedy, graph rewiring mechanisms have been proposed as preprocessing steps. Graph Echo State Networks (GESNs) are a reservoir computing model for graphs, where node embeddings are recursively computed by an untrained message-passing function. In this paper, we show that GESNs can achieve a significantly better accuracy on six heterophilic node classification tasks without altering the graph connectivity, thus suggesting a different route for addressing the over-squashing problem.

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Builds on 13 of its 27 references that are in the map. First posted on arXiv 13 Dec 2022.

Builds on

13 of 27 references.

References · 13

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,919
  3. 2018Relational inductive biases, deep learning, and graph networkscited by 1,360
  4. 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,102
  5. 2015Convolutional Networks on Graphs for Learning Molecular Fingerprintscited by 754
  6. 2020On the Bottleneck of Graph Neural Networks and its Practical Implicationscited by 631
  7. 2019Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological Viewcited by 545
  8. 2021Understanding over-squashing and bottlenecks on graphs via curvaturecited by 478
  9. 2019Diffusion Improves Graph Learningcited by 414
  10. 2015Diffusion-Convolutional Neural Networkscited by 268
  11. 2019A Gentle Introduction to Deep Learning for Graphscited by 108
  12. 2019Fast and Deep Graph Neural Networkscited by 35
1 more
  1. 2022Beyond Homophily with Graph Echo State Networkscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 5; 2024: 2; 2025: 5; 2026: 2.

14 papers.

Sort:

  1. 2023Adaptive Message Passing: A General Framework to Mitigate Oversmoothing, Oversquashing, and Underreachingcited by 24
  2. 2023Over-Squashing in Graph Neural Networks: A Comprehensive surveycited by 23
  3. 2023Exposition on over-squashing problem on GNNs: Current Methods, Benchmarks and Challengescited by 22
  4. 2025Oversmoothing, Oversquashing, Heterophily, Long-Range, and more: Demystifying Common Beliefs in Graph Machine Learningcited by 19
  5. 2023Correlation-aware Spatial-Temporal Graph Learning for Multivariate Time-series Anomaly Detectioncited by 18
  6. 2025Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsificationcited by 8
  7. 2025Over-squashing in Spatiotemporal Graph Neural Networkscited by 6
  8. 2024Foundations and Frontiers of Graph Learning Theorycited by 3
  9. 2023An Empirical Evaluation of Rewiring Approaches in Graph Neural Networkscited by 2
  10. 2025Performance Heterogeneity in Graph Neural Networks: Lessons for Architecture Design and Preprocessingcited by 2
  11. 2024Conditional Shift-Robust Conformal Prediction for Graph Neural Networkcited by 1
  12. 2025Adaptive Graph Rewiring to Mitigate Over-Squashing in Mesh-Based GNNs for Fluid Dynamics Simulationscited by 1
2 more
  1. 2026Probing Graph Neural Network Activation Patterns Through Graph Topologycited by 0
  2. 2026Reservoir-Based Graph Convolutional Networkscited by 0