Breaking Structural Isolation: Scalable Graph Clustering via Community-Aware Sampling and Structural Entropy

2026-07-06

AI Summary

This work addresses the “structural isolation” problem caused by mini-batch training in unsupervised graph clustering and proposes SCISE, a novel framework that uniquely integrates structural entropy constraints with community-aware sampling to preserve the global topological integrity of graphs. SCISE comprises three core components: the SECC operator enhances community cohesion, the CSampE mechanism mitigates global information loss by incorporating community context into sampling, and the StructCL module refines edge weights based on intra-batch structural similarity to learn high-order representations. Extensive experiments on six widely used benchmark datasets demonstrate that SCISE significantly outperforms current state-of-the-art methods, while ablation studies and robustness analyses further confirm its effectiveness and scalability.

Abstract

Unsupervised graph clustering is a fundamental technique for uncovering underlying semantic patterns in large-scale networks. Although Graph Contrastive Learning has demonstrated promising performance, existing methods often suffer from the "structural isolation" issue during mini-batch training, making it challenging to capture cohesive community structures that characterize the global topological distribution. To address these challenges, we propose SCISE, a Scalable unsupervised graph Clustering framework that preserves structural Integrity by synergizing community-aware sampling with constrained Structural Entropy. Specifically, we first introduce the Structural Entropy Community Constraint operator (SECC), which optimizes structural information within a constrained solution space to mitigate community fragmentation and enhance partition cohesion. Second, to prevent global information loss during batch training, we design a Community-Aware Sampling Expansion (CSampE) mechanism that incorporates the community context of target nodes into sampling batches, effectively breaking structural barriers and preserving topological integrity. Finally, we devise a Structural Contrastive Learning (StructCL) module that refines edge weights based on intra-batch structural similarity, guiding the encoder to learn representations in a higher-order structural space. Extensive experiments on six mainstream benchmark datasets demonstrate that SCISE significantly outperforms state-of-the-art algorithms, with ablation studies and robustness analyses further validating its effectiveness and reliability for real-world large-scale graphs.

Problem

• structural isolation
• graph clustering
• community structure
• structural entropy
• unsupervised learning

Innovation

• Structural Entropy
• Community-Aware Sampling
• Graph Clustering
• Contrastive Learning
• Scalable Graph Representation