Pseudo-label Enhanced Multi-view Deep Concept Factorization Fuzzy Clustering

• 1、School of Artificial Intelligence and Computer Science，Jiangnan University,Wu xi 214422

Abstract：Multi-view clustering has received much attention in recent years, which aims to improve the clustering performance by using cooperative learning of different views. In recent years, some effective multi-view clustering methods have been proposed, but these methods still have some issues that need to further research. First, most multi-view clustering methods only mine single-level information between views. Secondly, most of multi-view clustering methods based on the representation learning split the representation learning and clustering tasks To address the above problems, this paper proposes a new pseudo-label enhanced multi-view deep concept factorization fuzzy clustering. The method extracts multi-layer representations through multi-view concept factorization, explores the common representation by multi-view non-negative matrix factorization, and proposes a joint optimization framework in which multi-layer concept factorization learning, pseudo-label enhanced common representation learning, and clustering partition can optimize each other. The proposed algorithm is experimentally compared with a variety of related clustering methods, and the experimental results show that the performance of the proposed method outperforms the compared methods.

Keywords： artificial intelligence multi-view concept factorization pseudo-label learning fuzzy clustering