解决异质图节点相似性弱的问题，提升图神经网络表现
GLANCE: Graph Logic Attention Network with Cluster Enhancement for Heterophilous Graph Representation Learning
- 用逻辑推理与动态剪枝构建可解释的图表示
- 在Cornell、Texas等数据集上性能优于现有方法
- 适合需要可解释性的异质图学习场景
图神经网络在结构化数据学习中表现优异，但在异质图（相连节点特征或标签差异大）上常因盲目聚合邻居信息和缺乏高阶结构建模而失效。为此，本文提出GLANCE框架，融合逻辑引导推理、基于多头注意力的边剪枝与自适应聚类机制，实现图结构去噪与全局模式捕捉。该框架通过逻辑层生成可解释嵌入，利用注意力动态过滤冗余连接，并借助聚类发现潜在分组结构。在Cornell、Texas、Wisconsin等基准数据集上的实验表明，GLANCE在保持轻量的同时实现了有竞争力的性能，为异质图表征学习提供了鲁棒且可解释的解决方案。
原文摘要 · Abstract (English)
Graph Neural Networks (GNNs) have demonstrated significant success in learning from graph-structured data but often struggle on heterophilous graphs, where connected nodes differ in features or class labels. This limitation arises from indiscriminate neighbor aggregation and insufficient incorporation of higher-order structural patterns. To address these challenges, we propose GLANCE (Graph Logic Attention Network with Cluster Enhancement), a novel framework that integrates logic-guided reasoning, dynamic graph refinement, and adaptive clustering to enhance graph representation learning. GLANCE combines a logic layer for interpretable and structured embeddings, multi-head attention-based edge pruning for denoising graph structures, and clustering mechanisms for capturing global patterns. Experimental results in benchmark datasets, including Cornell, Texas, and Wisconsin, demonstrate that GLANCE achieves competitive performance, offering robust and interpretable solutions for heterophilous graph scenarios. The proposed framework is lightweight, adaptable, and uniquely suited to the challenges of heterophilous graphs.
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。