arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2512.02130cs.LG
收藏

跨视图拓扑感知图表示学习

Cross-View Topology-Aware Graph Representation Learning

Dept. of Mathematics, Georgia Institute of Technology, Atlanta, GA, USA Dept. of Computer Science \& Engineering, Texas A \& M University, College Station, TX, USA Dept. of Mathematical Sciences, The University of Texas at Dallas, Richardson, TX, USA

Ahmet Sami Korkmaz, Selim Coskunuzer, Md Joshem Uddin

AI总结:

GraphTCL通过整合结构嵌入与拓扑嵌入,利用跨视图对比学习提升图表示学习的鲁棒性和分类性能。

摘要:

图分类因其在化学、社交网络和生物信息学中的应用而受到广泛关注。尽管图神经网络(GNNs)能够有效捕捉局部结构模式,但它们往往忽视了对稳健表示学习至关重要的全局拓扑特征。在本文中,我们提出了GraphTCL,一种双视图对比学习框架,该框架整合了来自GNN的结构嵌入与通过持续同调导出的拓扑嵌入。通过跨视图对比损失对这些互补视图进行对齐,我们的方法提高了表示质量并改进了分类性能。在基准数据集上进行的广泛实验,包括TU和OGB分子图,表明GraphTCL在很大程度上优于最先进的基线。本研究强调了拓扑感知对比学习在推进图表示方法中的重要性。

英文摘要:

Graph classification has gained significant attention due to its applications in chemistry, social networks, and bioinformatics. While Graph Neural Networks (GNNs) effectively capture local structural patterns, they often overlook global topological features that are critical for robust representation learning. In this work, we propose GraphTCL, a dual-view contrastive learning framework that integrates structural embeddings from GNNs with topological embeddings derived from persistent homology. By aligning these complementary views through a cross-view contrastive loss, our method enhances representation quality and improves classification performance. Extensive experiments on benchmark datasets, including TU and OGB molecular graphs, demonstrate that GraphTCL consistently outperforms state-of-the-art baselines. This study highlights the importance of topology-aware contrastive learning for advancing graph representation methods.

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。

↑