On over-squashing in message passing neural networks: The impact of width, depth, and topology

F Di Giovanni, L Giusti, F Barbero… - International …, 2023‏ - proceedings.mlr.press
Abstract Message Passing Neural Networks (MPNNs) are instances of Graph Neural
Networks that leverage the graph to send messages over the edges. This inductive bias …

Revisiting over-smoothing and over-squashing using ollivier-ricci curvature

K Nguyen, NM Hieu, VD Nguyen, N Ho… - International …, 2023‏ - proceedings.mlr.press
Abstract Graph Neural Networks (GNNs) had been demonstrated to be inherently
susceptible to the problems of over-smoothing and over-squashing. These issues prohibit …

Understanding oversquashing in gnns through the lens of effective resistance

M Black, Z Wan, A Nayyeri… - … Conference on Machine …, 2023‏ - proceedings.mlr.press
Message passing graph neural networks (GNNs) are a popular learning architectures for
graph-structured data. However, one problem GNNs experience is oversquashing, where a …

Expander graph propagation

A Deac, M Lackenby… - Learning on Graphs …, 2022‏ - proceedings.mlr.press
Deploying graph neural networks (GNNs) on whole-graph classification or regression tasks
is known to be challenging: it often requires computing node features that are mindful of both …

FoSR: First-order spectral rewiring for addressing oversquashing in GNNs

K Karhadkar, PK Banerjee, G Montúfar - arxiv preprint arxiv:2210.11790, 2022‏ - arxiv.org
Graph neural networks (GNNs) are able to leverage the structure of graph data by passing
messages along the edges of the graph. While this allows GNNs to learn features …

Locality-aware graph-rewiring in gnns

F Barbero, A Velingker, A Saberi, M Bronstein… - arxiv preprint arxiv …, 2023‏ - arxiv.org
Graph Neural Networks (GNNs) are popular models for machine learning on graphs that
typically follow the message-passing paradigm, whereby the feature of a node is updated …

Probabilistic graph rewiring via virtual nodes

C Qian, A Manolache, C Morris… - Advances in Neural …, 2025‏ - proceedings.neurips.cc
Message-passing graph neural networks (MPNNs) have emerged as a powerful paradigm
for graph-based machine learning. Despite their effectiveness, MPNNs face challenges such …

A neural collapse perspective on feature evolution in graph neural networks

V Kothapalli, T Tirer, J Bruna - Advances in Neural …, 2023‏ - proceedings.neurips.cc
Graph neural networks (GNNs) have become increasingly popular for classification tasks on
graph-structured data. Yet, the interplay between graph topology and feature evolution in …

Over-squashing in graph neural networks: A comprehensive survey

S Akansha - arxiv preprint arxiv:2308.15568, 2023‏ - arxiv.org
Graph Neural Networks (GNNs) revolutionize machine learning for graph-structured data,
effectively capturing complex relationships. They disseminate information through …

Rewiring Techniques to Mitigate Oversquashing and Oversmoothing in GNNs: A Survey

H Attali, D Buscaldi, N Pernelle - arxiv preprint arxiv:2411.17429, 2024‏ - arxiv.org
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 …