Incomplete multiview clustering with bipartite tensors

Abstract

Incomplete Multi-view Clustering (IMC) serves as a pivotal approach in multi-view learning, as it effectively captures latent representations from incomplete multi-view data. This capability significantly enhances intelligent systems’ fault tolerance, reduces data acquisition costs, decreases dependency on data completeness in engineering applications, and improves overall robustness. However, existing incomplete multi-view clustering methods suffer from at least one of the following limitations: 1) they fail to fully explore the clustering structure of incomplete multi-view data; 2) they are sensitive to high missing ratios; 3) they treat different views equally, neglecting the inherent differences among views. This results in certain limitations for existing methods in practical applications, as they still rely on specific data completeness requirements. In this paper, we propose a novel tensor low-rank graph learning framework. First, we introduce a similarity matrix fitting module to construct independent low-dimensional representation matrices for different views under low-rank constraints and connectivity constraints. This method can effectively capture the clustering structure of the data. Furthermore, we introduce the tensor Schatten p-norm to reduce the sensitivity of the proposed method to high missing ratios. Then, we stack these low-dimensional representation matrices into a third-order tensor and leverage the advantages of rotation tensors in encoding higher-order correlations and complementary information between views to learn a low-dimensional consensus representation matrix for these low-dimensional representations. Additionally, we introduce an adaptive strategy to maximize the contribution of each view. Extensive experimental results indicate that IMCBT delivers superior performance in clustering tasks compared to various existing incomplete multi-view methods.