用拓扑特征增强图注意力网络，提升分类精度且不增加复杂度
LightTopoGAT: Enhancing Graph Attention Networks with Topological Features for Efficient Graph Classification
- 通过节点度和局部聚类系数增强节点特征
- 在MUTAG上准确率提升6.6%，PROTEINS上提升2.2%
- 轻量设计适合资源受限场景的图分类任务
图神经网络在图分类任务中表现优异，但通常计算开销大，难以有效捕捉全局图特性。我们提出LightTopoGAT，一种轻量级图注意力网络，通过引入节点度和局部聚类系数进行拓扑特征增强，提升图表示学习能力。该方法通过简化注意力机制保持参数效率，同时融合传统局部消息传递忽略的结构信息。在MUTAG、ENZYMES和PROTEINS三个基准数据集上的实验表明，LightTopoGAT优于GCN、GraphSAGE和标准GAT等基线模型，在MUTAG上准确率提升6.6%，在PROTEINS上提升2.2%。消融实验证明性能提升直接源于拓扑特征的引入，是一种无需增加架构复杂度的高效策略。
原文摘要 · Abstract (English)
Graph Neural Networks have demonstrated significant success in graph classification tasks, yet they often require substantial computational resources and struggle to capture global graph properties effectively. We introduce LightTopoGAT, a lightweight graph attention network that enhances node features through topological augmentation by incorporating node degree and local clustering coefficient to improve graph representation learning. The proposed approach maintains parameter efficiency through streamlined attention mechanisms while integrating structural information that is typically overlooked by local message passing schemes. Through comprehensive experiments on three benchmark datasets, MUTAG, ENZYMES, and PROTEINS, we show that LightTopoGAT achieves superior performance compared to established baselines including GCN, GraphSAGE, and standard GAT, with a 6.6 percent improvement in accuracy on MUTAG and a 2.2 percent improvement on PROTEINS. Ablation studies further confirm that these performance gains arise directly from the inclusion of topological features, demonstrating a simple yet effective strategy for enhancing graph neural network performance without increasing architectural complexity.
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。