Over-Squashing in GNNs and Causal Inference of Rewiring Strategies

• URL: http://arxiv.org/abs/2508.09265v1
• Date: Tue, 12 Aug 2025 18:16:45 GMT
• Title: Over-Squashing in GNNs and Causal Inference of Rewiring Strategies
• Abstract summary: Graph neural networks (GNNs) have exhibited state-of-the-art performance across wide-range of domains such as recommender systems, material design, and drug repurposing.<n>Message-passing GNNs suffer from over-squashing -- exponential compression of long-range information from distant nodes.<n>Rewiring techniques can ease this bottleneck; but their practical impacts are unclear due to the lack of a direct empirical over-squashing metric.
• Score: 1.6574413179773764
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Graph neural networks (GNNs) have exhibited state-of-the-art performance across wide-range of domains such as recommender systems, material design, and drug repurposing. Yet message-passing GNNs suffer from over-squashing -- exponential compression of long-range information from distant nodes -- which limits expressivity. Rewiring techniques can ease this bottleneck; but their practical impacts are unclear due to the lack of a direct empirical over-squashing metric. We propose a rigorous, topology-focused method for assessing over-squashing between node pairs using the decay rate of their mutual sensitivity. We then extend these pairwise assessments to four graph-level statistics (prevalence, intensity, variability, extremity). Coupling these metrics with a within-graph causal design, we quantify how rewiring strategies affect over-squashing on diverse graph- and node-classification benchmarks. Our extensive empirical analyses show that most graph classification datasets suffer from over-squashing (but to various extents), and rewiring effectively mitigates it -- though the degree of mitigation, and its translation into performance gains, varies by dataset and method. We also found that over-squashing is less notable in node classification datasets, where rewiring often increases over-squashing, and performance variations are uncorrelated with over-squashing changes. These findings suggest that rewiring is most beneficial when over-squashing is both substantial and corrected with restraint -- while overly aggressive rewiring, or rewiring applied to minimally over-squashed graphs, is unlikely to help and may even harm performance. Our plug-and-play diagnostic tool lets practitioners decide -- before any training -- whether rewiring is likely to pay off.

Related papers

• Graph Rewiring in GNNs to Mitigate Over-Squashing and Over-Smoothing: A Survey [10.05270465316705]
  We examine graph rewiring techniques, a class of methods designed to modify the graph topology to enhance information propagation in GNNs.<n>We provide a comprehensive review of state-of-the-art rewiring approaches, delving into their theoretical underpinnings, practical implementations, and performance trade-offs.
  arXiv  Detail & Related papers  (2026-05-01T11:16:19Z)
• Generalizing GNNs with Tokenized Mixture of Experts [75.8310720413187]
  We show that improving stability requires reducing reliance on shift-sensitive features, leaving an irreducible worst-case generalization floor.<n>We propose STEM-GNN, a pretrain-then-finetune framework with a mixture-of-experts encoder for diverse computation paths.<n>Across nine node, link, and graph benchmarks, STEM-GNN achieves a stronger three-way balance, improving robustness to degree/homophily shifts and to feature/edge corruptions while remaining competitive on clean graphs.
  arXiv  Detail & Related papers  (2026-02-09T22:48:30Z)
• Structural Invariance Matters: Rethinking Graph Rewiring through Graph Metrics [52.077620040518646]
  We provide the first systematic analysis of how rewiring affects a range of graph structural metrics.<n>We study seven diverse rewiring strategies and correlate changes in local and global graph properties with node classification accuracy.<n>Our results reveal a consistent pattern: successful rewiring methods tend to preserve local structure while allowing for flexibility in global connectivity.
  arXiv  Detail & Related papers  (2025-10-23T13:38:41Z)
• Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification [81.06278257153835]
  We propose a graph rewiring method that balances structural bottleneck reduction and graph property preservation.<n>Our method generates graphs with enhanced connectivity while maintaining sparsity and largely preserving the original graph spectrum.
  arXiv  Detail & Related papers  (2025-06-19T08:01:00Z)
• On Vanishing Gradients, Over-Smoothing, and Over-Squashing in GNNs: Bridging Recurrent and Graph Learning [20.302595624436183]
  Graph Neural Networks (GNNs) are models that leverage the graph structure to transmit information between nodes.<n>We show that a simple state-space formulation of a GNN effectively alleviates over-smoothing and over-squashing at no extra trainable parameter cost.
  arXiv  Detail & Related papers  (2025-02-15T14:43:41Z)
• Rewiring Techniques to Mitigate Oversquashing and Oversmoothing in GNNs: A Survey [0.0]
  Graph Neural Networks (GNNs) are powerful tools for learning from graph-structured data, but their effectiveness is often constrained by two critical challenges. Oversquashing, where the excessive compression of information from distant nodes results in significant information loss, and oversmoothing, where repeated message-passing iterations homogenize node representations, obscuring meaningful distinctions. In this survey, we examine graph rewiring techniques, a class of methods designed to address these structural bottlenecks by modifying graph topology to enhance information diffusion.
  arXiv  Detail & Related papers  (2024-11-26T13:38:12Z)
• The Effectiveness of Curvature-Based Rewiring and the Role of Hyperparameters in GNNs Revisited [0.7373617024876725]
  Message passing is the dominant paradigm in Graph Neural Networks (GNNs) Recent efforts have focused on graph rewiring techniques, which disconnect the input graph originating from the data and the computational graph, on which message passing is performed. While oversquashing has been demonstrated in synthetic datasets, in this work we reevaluate the performance gains that curvature-based rewiring brings to real-world datasets.
  arXiv  Detail & Related papers  (2024-07-12T16:03:58Z)
• Learning to Reweight for Graph Neural Network [63.978102332612906]
  Graph Neural Networks (GNNs) show promising results for graph tasks. Existing GNNs' generalization ability will degrade when there exist distribution shifts between testing and training graph data. We propose a novel nonlinear graph decorrelation method, which can substantially improve the out-of-distribution generalization ability.
  arXiv  Detail & Related papers  (2023-12-19T12:25:10Z)
• Latent Graph Inference with Limited Supervision [58.54674649232757]
  Latent graph inference (LGI) aims to jointly learn the underlying graph structure and node representations from data features. Existing LGI methods commonly suffer from the issue of supervision starvation, where massive edge weights are learned without semantic supervision and do not contribute to the training loss. In this paper, we observe that this issue is actually caused by the graph sparsification operation, which severely destroys the important connections established between pivotal nodes and labeled ones.
  arXiv  Detail & Related papers  (2023-10-06T15:22:40Z)
• Mitigating Over-Smoothing and Over-Squashing using Augmentations of Forman-Ricci Curvature [1.1126342180866644]
  We propose a rewiring technique based on Augmented Forman-Ricci curvature (AFRC), a scalable curvature notation. We prove that AFRC effectively characterizes over-smoothing and over-squashing effects in message-passing GNNs.
  arXiv  Detail & Related papers  (2023-09-17T21:43:18Z)
• Resisting Graph Adversarial Attack via Cooperative Homophilous Augmentation [60.50994154879244]
  Recent studies show that Graph Neural Networks are vulnerable and easily fooled by small perturbations. In this work, we focus on the emerging but critical attack, namely, Graph Injection Attack. We propose a general defense framework CHAGNN against GIA through cooperative homophilous augmentation of graph data and model.
  arXiv  Detail & Related papers  (2022-11-15T11:44:31Z)
• Scaling Up Graph Neural Networks Via Graph Coarsening [18.176326897605225]
  Scalability of graph neural networks (GNNs) is one of the major challenges in machine learning. In this paper, we propose to use graph coarsening for scalable training of GNNs. We show that, simply applying off-the-shelf coarsening methods, we can reduce the number of nodes by up to a factor of ten without causing a noticeable downgrade in classification accuracy.
  arXiv  Detail & Related papers  (2021-06-09T15:46:17Z)
• Understanding and Resolving Performance Degradation in Graph Convolutional Networks [105.14867349802898]
  Graph Convolutional Network (GCN) stacks several layers and in each layer performs a PROPagation operation (PROP) and a TRANsformation operation (TRAN) for learning node representations over graph-structured data. GCNs tend to suffer performance drop when the model gets deep. We study performance degradation of GCNs by experimentally examining how stacking only TRANs or PROPs works.
  arXiv  Detail & Related papers  (2020-06-12T12:12:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.