标签
This paper proposes PairAlign, a pair-centric graph rewiring framework that uses optimal transport-guided communication alignment to alleviate over-squashing in message-passing neural networks, with theoretical analysis and experiments on standard benchmarks.
提出了 Schreier-Coset 图重连（Schreier-Coset Graph Rewiring），一种基于群论的图重连方法，用于 GNN，通过改善谱间隙和有效电阻来缓解过度挤压问题。实验结果表明，该方法在多种学习任务中显著降低了有效电阻。