Score: 1

Cross-View Topology-Aware Graph Representation Learning

Published: December 1, 2025 | arXiv ID: 2512.02130v1

By: Ahmet Sami Korkmaz, Selim Coskunuzer, Md Joshem Uddin

Potential Business Impact:

Helps computers understand complex data patterns better.

Business Areas:
Image Recognition Data and Analytics, Software

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.

Country of Origin
🇺🇸 United States

Page Count
13 pages

Category
Computer Science:
Machine Learning (CS)