arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2512.13617cs.LG
收藏

LightTopoGAT: 通过拓扑特征增强图注意力网络以实现高效的图分类

LightTopoGAT: Enhancing Graph Attention Networks with Topological Features for Efficient Graph Classification

Indira Gandhi National Open University (IGNOU)(英迪拉·甘地国立开放大学(IGNOU))

Ankit Sharma, Sayan Roy Gupta

AI总结:

LightTopoGAT通过引入拓扑特征增强图注意力网络,提升图分类性能,实现轻量高效模型

摘要:

图神经网络在图分类任务中已展现出显著的成功,但它们通常需要大量的计算资源,并且难以有效捕捉全局图属性。我们介绍了LightTopoGAT,一种轻量级的图注意力网络,通过引入节点度和局部聚类系数等拓扑特征来增强节点特征,以提高图表示学习的效果。所提出的方法通过简化注意力机制保持参数效率,同时整合通常被局部消息传递方案忽略的结构信息。通过在三个基准数据集MUTAG、ENZYMES和PROTEINS上的全面实验,我们展示了LightTopoGAT在MUTAG数据集上比GCN、GraphSAGE和标准GAT等现有基线方法在准确率上提高了6.6%,在PROTEINS数据集上提高了2.2%。消融研究进一步证实,这些性能提升直接来自于拓扑特征的引入,证明了一种简单但有效的策略,可以在不增加架构复杂度的情况下提升图神经网络的性能。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑