HTG-GCL: Leveraging Hierarchical Topological Granularity from Cellular Complexes for Graph Contrastive Learning

2025-11-30

AI Summary

Existing graph contrastive learning (GCL) methods struggle to identify task-relevant topological structures and fail to adaptively learn multi-granular topological representations required by downstream tasks. To address this, we propose HTG-GCL—a hierarchical topological graph GCL framework. First, we introduce the novel concept of *topological granularity* and construct multi-scale contrastive graph views grounded in cycle-based cell complexes. Second, we design a multi-granularity decoupled contrastive mechanism that jointly models coarse-grained global structure and fine-grained local patterns. Third, we propose an uncertainty-aware granularity weighting strategy to dynamically fuse hierarchical topological information. Extensive experiments on multiple benchmark datasets demonstrate that HTG-GCL consistently outperforms state-of-the-art GCL methods, validating its effectiveness in enhancing representation discriminability, task adaptability, and robustness.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Reasoning under Uncertainty: Graphical Models
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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.

Problem

• Identifies task-relevant topological structures in graphs
• Adapts to varying coarse-to-fine topological granularities across tasks
• Mitigates misleading semantics from specific granularities via uncertainty weighting

Innovation

• Generates multi-scale ring-based cellular complexes
• Applies multi-granularity decoupled contrast mechanism
• Uses uncertainty-based weighting for granularity selection