Interactive dual contrastive fusion for multi-view clustering with local structure preservation

Abstract

In recent years, compared with traditional shallow methods, deep multi-view clustering has achieved remarkable results in latent feature learning of multi-view data. By implementing a contrastive fusion between different views, the discriminative capability of the latent features is further strengthened. However, the lack of structural guidance for clustering and conflicts between multi-objective losses often lead to suboptimal results. To address these problems, a novel Interactive dual Contrastive fusion for Multi-View Clustering with local structure preservation (ICMVC) is proposed in this paper. By performing contrastive fusion at both feature and cluster levels, this method obtains compact similarity matrix within clusters and well-separated semantic labels between clusters. In particular, an interaction mechanism based on local structure preservation is designed to effectively resolve conflicts between multi-objective losses at different levels. This mutual guidance between different levels promotes the overall clustering performance. Experiments on several benchmarks show that the proposed method not only achieves excellent clustering performance, but also enhances the stability of convergence.