通过动态三角剖分重连图结构，提升GNN的信息传播效率。
Dynamic Triangulation-Based Graph Rewiring for Graph Neural Networks
- 从多视角图中学习选择相关三角形，构建非平面三角剖分。
- 重连后图的直径更小、谱间隙更大、有效电阻更低，性能更优。
- 适用于同质与异质图节点分类，显著超越现有方法。
图神经网络（GNN）已成为图结构数据学习的主流范式，但其性能受限于图拓扑固有的问题，尤其是信息压缩和过度平滑。近期图重连方法通过修改图拓扑来缓解这些问题。本文提出TRIGON框架，通过学习从多个图视图中选择相关三角形，构建丰富且非平面的三角剖分。联合优化三角形选择与下游分类性能，所生成的重连图具有更优的结构特性：直径更小、谱间隙更大、有效电阻更低。实验证明，TRIGON在多种同质与异质基准上的节点分类任务中均优于现有先进方法。
原文摘要 · Abstract (English)
Graph Neural Networks (GNNs) have emerged as the leading paradigm for learning over graph-structured data. However, their performance is limited by issues inherent to graph topology, most notably oversquashing and oversmoothing. Recent advances in graph rewiring aim to mitigate these limitations by modifying the graph topology to promote more effective information propagation. In this work, we introduce TRIGON, a novel framework that constructs enriched, non-planar triangulations by learning to select relevant triangles from multiple graph views. By jointly optimizing triangle selection and downstream classification performance, our method produces a rewired graph with markedly improved structural properties such as reduced diameter, increased spectral gap, and lower effective resistance compared to existing rewiring methods. Empirical results demonstrate that TRIGON outperforms state-of-the-art approaches on node classification tasks across a range of homophilic and heterophilic benchmarks.
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。