Tensorized Tri-Factor Decomposition for Multi-View Clustering

Abstract

Multi-view clustering leverages the complementary and compatible information among various views to achieve superior clustering outcomes. The approach of multi-view clustering through non-negative matrix factorization (NMF) has garnered extensive interest, attributed to its remarkable interpretability and clustering efficacy. Nonetheless, existing NMF-based multi-view subspace clustering methods fall short in thoroughly harnessing the complementary information across different views, potentially impairing clustering performance. To mitigate this issue, we introduce an orthogonal semi-nonnegative matrix tri-factorization model. This model excels in clustering interpretability, enabling the direct derivation of cluster labels from the clustering indicator matrix, thereby eliminating the need for post-processing. Our model employs tensor Schatten p-norm as a constraint, adeptly capturing both the complementary information and spatial structure information across views. Extensive experimental evaluations on a variety of benchmark datasets affirm the superior clustering performance of our proposed method.