Diverse and Common Multi-View Subspace Clustering

Multi-view subspace clustering aims to divide a set of multi-source data into underlying groups. Exploiting common and complementary information among different views can improve the clustering performance. In this paper, we propose a multi-view subspace clustering model. It can simultaneously learn a common representation among all views and diverse representations to explore common and complementary information. Moreover, we achieve subspace learning and spectral clustering into an optimization model, which guarantees the consistence of clustering among different views. Experimental results on text dataset and face dataset demonstrate that our proposed method over other state-of-the-arts.