---
title: "Graph Embedded Contrastive Learning for Multi-View Clustering"
authors:
  - "Hongqing He"
  - "Jie Xu"
  - "Guoqiu Wen"
  - "Yazhou Ren"
  - "Na Zhao"
  - "Xiaofeng Zhu"
doi: "10.24963/ijcai.2025/594"
url: "https://ijcai.org/proceedings/2025/594"
pdf: "https://ijcai.org/proceedings/2025/0594.pdf"
venue: "Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"
year: 2025
pages: "5336-5344"
track: "Main Track"
keywords:
  - "Machine Learning: ML: Unsupervised learning"
  - "Machine Learning: ML: Multi-view learning"
  - "Machine Learning: ML: Self-supervised Learning"
  - "Machine Learning: ML: Clustering"
---

# Graph Embedded Contrastive Learning for Multi-View Clustering

Hongqing He, Jie Xu, Guoqiu Wen, Yazhou Ren, Na Zhao, Xiaofeng Zhu

*Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence*, pages 5336-5344. DOI: [10.24963/ijcai.2025/594](https://doi.org/10.24963/ijcai.2025/594)

## Abstract

Recently, numerous multi-view clustering (MVC) and multi-view graph clustering (MVGC) methods have been proposed. Despite significant progress, they still face two issues: I) MVC and MVGC are often developed independently for multi-view and multi-graph data. They have redundancy but lack a unified methodology to combine their strengths. II) Contrastive learning is usually adopted to explore the associations across multiple views. However, traditional contrastive losses ignore the neighbor relationship in multi-view scenarios and easily lead to false associations in sample pairs. To address these issues, we propose Graph Embedded Contrastive Learning for Multi-View Clustering. Concretely, we propose a process of view-specific pre-training with adaptive graph convolution to make our method compatible with both multi-view and multi-graph data, which aggregates the graph information into data and leverages autoencoders to learn view-specific representations. Furthermore, to explore the view-cross associations, we introduce the process of view-cross contrastive learning and clustering, where we propose the graph-guided contrastive learning that can generate global graph to mitigate the false association issue as well as the cluster-guided contrastive clustering for improving the model robustness. Finally, extensive experiments demonstrate that our method achieves superior performance on both MVC and MVGC tasks.