Multigranularity Information Fused Contrastive Learning With Multiview Clustering

Contrastive multiview clustering (MVC) has emerged as a mainstream approach in MVC due to its superior representation learning capabilities. Traditional contrastive multiview learning methods extract both low- and high-level information from raw data. However, only high-level information is utilized for clustering. Since both types of information are essential for effective clustering, this limitation hampers performance. Moreover, effectively quantifying the importance of different views remains a critical challenge in contrastive MVC. Additionally, the absence of structural information during clustering further weakens clustering performance. To address these issues, this article proposes a multigranularity (MG) information fused contrastive learning with MVC (MGCMVC). Inspired by the concept of MG, low- and high-level features are reconstructed into fine- and coarse-granularity features. First, an MG adaptive weighting sample-level contrastive learning mechanism is introduced to fuse MG features to enhance clustering performance and mitigate clustering performance degradation caused by variations in view quality. Second, a structure-oriented cluster-level contrastive learning approach is designed to preserve structural information and enforce cross-view clustering consistency. Extensive and comprehensive experiments on ten widely used datasets demonstrate that MGCMVC achieves the state-of-the-art performance. The source code is available at https://github.com/Luyangabc/MGCMVC.