End-to-end Multi-view Fuzzy Clustering With Double Representation Learning and Visible-hidden View Cooperation

Multi-view clustering has received great attention in recent years for the potential in clustering performance improvement by using cooperative learning of different views. Despite the considerable progress, a few issues remain: (1) real multi-view data contains redundant features and noises that lead to unsatisfactory clustering performance; (2) most existing multi-view clustering methods only mine the shared information between views and ignore the specific information within views; (3) most multi-view clustering methods are based on a two-step framework that learn the hidden view representation and then perform clustering, overlooking the correlation between the two processes. Although some approaches have been proposed to deal with these issues, they cannot them simultaneously. To this end, we propose an end-to-end multi-view fuzzy clustering (EMVFC). First, we construct a multi-view fuzzy clustering framework to mine the specific information of the visible views. Second, to reduce the impact of redundant features and noises on clustering performance, we introduce the orthogonal projection matrix into the clustering framework to learn the low-dimensional representation of the visible views. Meanwhile, this procedure is integrated into the clustering framework. Third, we explore the shared hidden view representation between the visible views by multi-view non-negative matrix factorization and integrate it into the clustering framework to realize visible-hidden view cooperation learning. Finally, the shared hidden view representation learning between visible views, the low-dimensional representation learning of visible views, and the clustering partition of multi-view data negotiate with each other in the end-to-end learning framework. Extensive experiments on benchmark multi-view datasets indicate the superiority of the proposed method over state-of-the-art methods.