---
title: "Efficient Multi-view Clustering via Reinforcement Contrastive Learning"
authors:
  - "Qianqian Wang"
  - "Haiming Xu"
  - "Zihao Zhang"
  - "Zhiqiang Tao"
  - "Quanxue Gao"
doi: "10.24963/ijcai.2025/708"
url: "https://ijcai.org/proceedings/2025/708"
pdf: "https://ijcai.org/proceedings/2025/0708.pdf"
venue: "Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"
year: 2025
pages: "6361-6369"
track: "Main Track"
keywords:
  - "Machine Learning: ML: Reinforcement learning"
---

# Efficient Multi-view Clustering via Reinforcement Contrastive Learning

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

*Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence*, pages 6361-6369. DOI: [10.24963/ijcai.2025/708](https://doi.org/10.24963/ijcai.2025/708)

## 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.