paper-with-me

홈 › Papers

Effects of Random Edge-Dropping on Over-Squashing in Graph Neural Networks

2025-02-11 · Jasraj Singh, Keyue Jiang, Brooks Paige, Laura Toni

Message Passing Neural Networks (MPNNs) are a class of Graph Neural Networks (GNNs) that leverage the graph topology to propagate messages across increasingly larger neighborhoods. The message-passing scheme leads to two distinct challenges: over-smoothing and over-squashing. While several algorithms, e.g. DropEdge and its variants -- DropNode, DropAgg and DropGNN -- have successfully addressed the over-smoothing problem, their impact on over-squashing remains largely unexplored. This represents a critical gap in the literature as failure to mitigate over-squashing would make these methods unsuitable for long-range tasks. In this work, we take the first step towards closing this gap by studying the aforementioned algorithms in the context of over-squashing. We present novel theoretical results that characterize the negative effects of DropEdge on sensitivity between distant nodes, suggesting its unsuitability for long-range tasks. Our findings are easily extended to its variants, allowing us to build a comprehensive understanding of how they affect over-squashing. We evaluate these methods using real-world datasets, demonstrating their detrimental effects. Specifically, we show that while DropEdge-variants improve test-time performance in short range tasks, they deteriorate performance in long-range ones. Our theory explains these results as follows: random edge-dropping lowers the effective receptive field of GNNs, which although beneficial for short-range tasks, misaligns the models on long-range ones. This forces the models to overfit to short-range artefacts in the training set, resulting in poor generalization. Our conclusions highlight the need to re-evaluate various methods designed for training deep GNNs, with a renewed focus on modelling long-range interactions.

📄 PDF Abstract BibTeX arXiv:2502.07364

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

RADE: Random Add-Drop Edge as a Regularizer

2026-05-30 · Danial Saber, Amirali Salehi-Abari arxiv

Graph Neural Networks (GNNs) suffer from overfitting and over-squashing of long-range information. Stochastic graph augmentations (e.g., edge deletion) regularize training against overfitting but can introduce train-infe…

Mitigating Over-Smoothing and Over-Squashing using Augmentations of Forman-Ricci Curvature

2023-09-17 · Lukas Fesser, Melanie Weber

While Graph Neural Networks (GNNs) have been successfully leveraged for learning on graph-structured data across domains, several potential pitfalls have been described recently. Those include the inability to accurately…

Oversquashing in GNNs through the lens of information contraction and graph expansion

2022-08-06 · Pradeep Kr. Banerjee, Kedar Karhadkar, Yu Guang Wang, Uri Alon 외

The quality of signal propagation in message-passing graph neural networks (GNNs) strongly influences their expressivity as has been observed in recent works. In particular, for prediction tasks relying on long-range int…

graph construction

Local Virtual Nodes for Alleviating Over-Squashing in Graph Neural Networks

2025-08-28 · Tuğrul Hasan Karabulut, İnci M. Baytaş arxiv

Over-squashing is a challenge in training graph neural networks for tasks involving long-range dependencies. In such tasks, a GNN's receptive field should be large enough to enable communication between distant nodes. Ho…

Node Classification

RankedDrop: Enhancing Deep Graph Convolutional Networks Training

2021-09-29 · Quentin Petit, Chong Li, Kelun Chai, Serge G Petiton

Graph Neural Networks (GNNs) are playing a more and more important role for analyzing unstructured data from the complex real world. Introducing random edge dropping from the input graph at training epochs could reduce o…