Guardado en:
Detalles Bibliográficos
Autores principales: Benoit, Alexandre, Aitken, Catherine, He, Yu
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2510.20556
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911228286205952
author Benoit, Alexandre
Aitken, Catherine
He, Yu
author_facet Benoit, Alexandre
Aitken, Catherine
He, Yu
contents Graph rewiring has emerged as a key technique to alleviate over-squashing in Graph Neural Networks (GNNs) and Graph Transformers by modifying the graph topology to improve information flow. While effective, rewiring inherently alters the graph's structure, raising the risk of distorting important topology-dependent signals. Yet, despite the growing use of rewiring, little is known about which structural properties must be preserved to ensure both performance gains and structural fidelity. In this work, we provide the first systematic analysis of how rewiring affects a range of graph structural metrics, and how these changes relate to downstream task performance. We study seven diverse rewiring strategies and correlate changes in local and global graph properties with node classification accuracy. Our results reveal a consistent pattern: successful rewiring methods tend to preserve local structure while allowing for flexibility in global connectivity. These findings offer new insights into the design of effective rewiring strategies, bridging the gap between graph theory and practical GNN optimization.
format Preprint
id arxiv_https___arxiv_org_abs_2510_20556
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Structural Invariance Matters: Rethinking Graph Rewiring through Graph Metrics
Benoit, Alexandre
Aitken, Catherine
He, Yu
Machine Learning
Artificial Intelligence
Graph rewiring has emerged as a key technique to alleviate over-squashing in Graph Neural Networks (GNNs) and Graph Transformers by modifying the graph topology to improve information flow. While effective, rewiring inherently alters the graph's structure, raising the risk of distorting important topology-dependent signals. Yet, despite the growing use of rewiring, little is known about which structural properties must be preserved to ensure both performance gains and structural fidelity. In this work, we provide the first systematic analysis of how rewiring affects a range of graph structural metrics, and how these changes relate to downstream task performance. We study seven diverse rewiring strategies and correlate changes in local and global graph properties with node classification accuracy. Our results reveal a consistent pattern: successful rewiring methods tend to preserve local structure while allowing for flexibility in global connectivity. These findings offer new insights into the design of effective rewiring strategies, bridging the gap between graph theory and practical GNN optimization.
title Structural Invariance Matters: Rethinking Graph Rewiring through Graph Metrics
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2510.20556