Proceedings

Efficient Multi-view Clustering via Reinforcement Contrastive Learning

Qianqian Wang, Haiming Xu, Zihao Zhang, Zhiqiang Tao, Quanxue Gao

Download BibTeX Cite

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. Main Track. Pages 6361-6369.

https://doi.org/10.24963/ijcai.2025/708

Keywords

  • Machine Learning: ML: Reinforcement learning

Abstract

Contrastive multi-view clustering has demonstrated remarkable potential in complex data analysis, yet existing approaches face two critical challenges: difficulty in constructing high-quality positive and negative pairs and high computational overhead due to static optimization strategies. To address these challenges, we propose an innovative efficient Multi-View Clustering framework with Reinforcement Contrastive Learning (EMVCRCL). Our key innovation is developing a reinforcement contrastive learning paradigm for dynamic clustering optimization. First, we leverage multi-view contrastive learning to obtain latent features, which are then sent to the reinforcement learning module to refine low-quality features. Specifically, it selects high-confident features to guide the positive/negative pair construction of contrastive learning. For the low-confident features, it utilizes the prior balanced distribution to adjust their assignment. Extensive experimental results showcase the effectiveness and superiority of our proposed method on multiple benchmark datasets.

Qianqian Wang, Haiming Xu, Zihao Zhang, Zhiqiang Tao, and Quanxue Gao. 2025. Efficient Multi-view Clustering via Reinforcement Contrastive Learning. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. IJCAI, 6361–6369. https://doi.org/10.24963/ijcai.2025/708
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards