---
title: "Robust Contrastive Graph Clustering with Adaptive Local-Global Integration"
authors:
  - "Lei Zhang"
  - "Fubo Sun"
  - "Haipeng Yang"
  - "Zhong Guan"
  - "Likang Wu"
doi: "10.24963/ijcai.2026/357"
url: "https://ijcai.org/proceedings/2026/357"
pdf: "https://ijcai.org/proceedings/2026/0357.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "3214-3222"
track: "Main Track"
keywords:
  - "Machine Learning: Multi-view learning"
  - "Data Mining: Mining text, web, social media"
  - "Data Mining: Mining graphs"
---

# Robust Contrastive Graph Clustering with Adaptive Local-Global Integration

Lei Zhang, Fubo Sun, Haipeng Yang, Zhong Guan, Likang Wu

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 3214-3222. DOI: [10.24963/ijcai.2026/357](https://doi.org/10.24963/ijcai.2026/357)

## Abstract

Graph clustering is essential in graph analysis for revealing structural patterns and node communities. Despite recent advances in self-supervised contrastive learning that have improved clustering via structural and attribute signals, existing methods still struggle to flexibly capture high-order local structures and often overlook global semantics in complex graphs. These limitations lead to suboptimal node representations, especially in real-world graphs with fragmented structures and ambiguous cluster boundaries. To address these limitations, a contrastive graph clustering framework is proposed to jointly integrate multi-scale local structures with global semantics via attention mechanisms. At the local level, GNN-based topological signals extracted from multiple propagation depths are adaptively fused through attention-based weighting to capture multi-scale neighborhood features. At the global level, semantic prototypes derived from dynamically evolving cluster centers are adaptively aggregated through attention to guide node representations and enhance inter-cluster separability. The model is trained under a dual-view contrastive learning paradigm with a hybrid objective that combines instance-level and structure-aware losses to improve representation robustness and discrimination. Experiments on eight real-world graph datasets demonstrate that our method achieves competitive clustering performance. Code is  available at https://github.com/vege12138/w2.