Saved in:
Bibliographic Details
Main Authors: You, Zinuo, Zheng, Jin, Cartlidge, John
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.06443
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914465495121920
author You, Zinuo
Zheng, Jin
Cartlidge, John
author_facet You, Zinuo
Zheng, Jin
Cartlidge, John
contents Existing graph neural networks typically rely on heuristic choices for hidden dimensions and propagation depths, which often lead to severe information loss during propagation, known as over-squashing. To address this issue, we propose Channel Capacity Constrained Estimation (C3E), a novel framework that formulates the selection of hidden dimensions and depth as a nonlinear programming problem grounded in information theory. Through modeling spectral graph neural networks as communication channels, our approach directly connects channel capacity to hidden dimensions, propagation depth, propagation mechanism, and graph structure. Extensive experiments on nine public datasets demonstrate that hidden dimensions and depths estimated by C3E can mitigate over-squashing and consistently improve representation learning. Experimental results show that over-squashing occurs due to the cumulative compression of information in representation matrices. Furthermore, our findings show that increasing hidden dimensions indeed mitigate information compression, while the role of propagation depth is more nuanced, uncovering a fundamental balance between information compression and representation complexity.
format Preprint
id arxiv_https___arxiv_org_abs_2511_06443
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle How Wide and How Deep? Mitigating Over-Squashing of GNNs via Channel Capacity Constrained Estimation
You, Zinuo
Zheng, Jin
Cartlidge, John
Machine Learning
Existing graph neural networks typically rely on heuristic choices for hidden dimensions and propagation depths, which often lead to severe information loss during propagation, known as over-squashing. To address this issue, we propose Channel Capacity Constrained Estimation (C3E), a novel framework that formulates the selection of hidden dimensions and depth as a nonlinear programming problem grounded in information theory. Through modeling spectral graph neural networks as communication channels, our approach directly connects channel capacity to hidden dimensions, propagation depth, propagation mechanism, and graph structure. Extensive experiments on nine public datasets demonstrate that hidden dimensions and depths estimated by C3E can mitigate over-squashing and consistently improve representation learning. Experimental results show that over-squashing occurs due to the cumulative compression of information in representation matrices. Furthermore, our findings show that increasing hidden dimensions indeed mitigate information compression, while the role of propagation depth is more nuanced, uncovering a fundamental balance between information compression and representation complexity.
title How Wide and How Deep? Mitigating Over-Squashing of GNNs via Channel Capacity Constrained Estimation
topic Machine Learning
url https://arxiv.org/abs/2511.06443