Auto-weighted multi-view co-clustering via fast matrix factorization. (June 2020)

• Record Type: Journal Article
• Authors: Nie, Feiping; Shi, Shaojun; Li, Xuelong
• Is Part Of: Pattern recognition. Volume 102(2020:Jun.)
• Publication Date: 2020-06
• Subjects: Co-clustering -- Multi-view data -- Matrix factorization -- Auto-weighted; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2020.107207
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: Distinguishing the existing multi-view clustering methods, the proposed approaches involve constraints of indicator matrix in matrix decomposition. Due to the existence of constraints, we can directly acquire the clustering results of samples and features. Thus, the proposed methods are highly efficient for the clustering problem of solving multi-view data sets. According to the importance of each view for the clustering task, the proposed approaches automatically learn the weight factor in a re-weighted manner. Moreover, the proposed methods are free parameter which make them be more practical. Comparing with graph-based multi-view clustering algorithms, the computational complexity of the proposed methods is same as the traditional K-means algorithm due to the fact that they do not need eigenvalue decomposition in solving process which is heavy computation burden for multi-view data sets. Abstract: Multi-view clustering is a hot research topic in machine learning and pattern recognition, however, it remains high computational complexity when clustering multi-view data sets. Although a number of approaches have been proposed to accelerate the computational efficiency, most of them do not consider the data duality between features and samples. In this paper, we propose a novel co-clustering approach termed as Fast Multi-view Bilateral K-means (FMVBKM), which can implement clustering task on row and column of the input data matrix, simultaneously. Specifically, FMVBKM applies the relaxed K-means clustering technique to multi-view data clustering. In addition, to decrease information loss in matrix factorization, we further introduce a new co-clustering method named as Fast Multi-view Matrix Tri-Factorization (FMVMTF). Extensive experimental results on six benchmark data sets show that the proposed two approaches not only have comparable clustering performance but also present the high computational efficiency, in comparison with state-of-the-art multi-view clustering methods.