Adaptive multi-view subspace clustering algorithm based on representative features and redundant instances

The goal of multi-view subspace clustering is to group objects into distinct clusters using information from multiple views, which remains challenging when dealing with diverse data sources. However, the learned consensus matrix of most of the existing approaches maybe inaccurate and lead to unsatisfactory clustering performance due to the following two limitations. The first one is that the representative features are treated equally with the other unimportant features, thus resulting in the incapability of capturing the latent information in each view. Second, the redundant information is not considered from the viewpoints, which raises a negative impact caused by certain noise. This paper proposes a novel adaptive multi-view subspace clustering based on representative features and redundant instances (AMC2R) to address these two challenging issues. Specifically, the proposed algorithm focuses on the representative feature, in which a weighted matrix is designed for each view to dynamically obtain a consensus matrix using the information conveyed by each feature. After that, all the views are concatenated together to utilize the complementary information across the views, and a matrix under l 2 , 1-norm constraint is used to obtain the final consensus matrix to eliminate the negative impact raised by the redundant information. A unified framework is then designed to integrate the above steps. In this way, the representative information and the redundant information can simultaneously interact with one another during the iterations. Experimental results on different datasets demonstrate the effectiveness of the proposed algorithm and have achieved excellent results on Accuracy (ACC), Normalized Mutual Information (NMI), and Adjusted Rand Index (ARI).