HTG-GCL: Leveraging Hierarchical Topological Granularity from Cellular Complexes for Graph Contrastive Learning
Preprint
Abstract
Graph contrastive learning (GCL) aims to learn discriminative semantic invariance by contrasting different views of the same graph that share critical topological patterns. However, existing GCL approaches with structural augmentations often struggle to identify task-relevant topological structures, let alone adapt to the varying coarse-to-fine topological granularities required across different downstream tasks. To remedy this issue, we introduce Hierarchical Topological Granularity Graph Contrastive Learning (HTG-GCL), a novel framework that leverages transformations of the same graph to generate multi-scale ring-based cellular complexes, embodying the concept of topological granularity, thereby generating diverse topological views. Recognizing that a certain granularity may contain misleading semantics, we propose a multi-granularity decoupled contrast and apply a granularity-specific weighting mechanism based on uncertainty estimation. Comprehensive experiments on various benchmarks demonstrate the effectiveness of HTG-GCL, highlighting its superior performance in capturing meaningful graph representations through hierarchical topological information.Keywords
All Related Versions
This publication has 4 references indexed in Scilit:
- CellCLAT: Preserving Topology and Trimming Redundancy in Self-Supervised Cellular Contrastive Learning2025
- Graph Learning with Distributional Edge Layouts2025
- Modeling Multiple Views via Implicitly Preserving Global Consistency and Local ComplementarityIEEE Transactions on Knowledge and Data Engineering, 2022
- Toward a spectral theory of cellular sheavesJournal of Applied and Computational Topology, 2019