发现图重连需保局部结构，才能提升模型性能
Structural Invariance Matters: Rethinking Graph Rewiring through Graph Metrics
- 分析七种重连方法对图结构指标的影响
- 保局部结构的重连能显著提升分类准确率
- 适合关注GNN结构优化的研究者参考
图重连已成为缓解图神经网络（GNN）与图变换器中信息过挤的关键技术，通过调整图拓扑改善信息流动。尽管有效，重连会改变图结构，可能破坏依赖拓扑的重要信号。然而，现有研究极少探讨哪些结构特性必须保留以兼顾性能与结构保真度。本文首次系统分析了重连对多种图结构度量的影响，并揭示其与下游任务性能的关系。我们考察了七种不同重连策略，关联局部与全局图属性变化与节点分类准确率。结果表明：成功的重连方法通常保持局部结构，同时允许全局连接灵活调整。这一发现为设计高效重连策略提供了新思路，弥合了图论与实际GNN优化之间的差距。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。