Multi-view Fuzzy Clustering With Anchor Graph

Graph-based multi-view clustering has become a powerful tool for multi-view data analysis by jointly capturing structural relationships across heterogeneous views. Despite significant advances in this field, several limitations persist. Most graph-based multi-view algorithms employ a relaxation-and-discretization two-stage paradigm to obtain clustering assignments, which may significantly undermine information preservation and clustering performance. Moreover, these methods often suffer from quadratic or even cubic time complexity, rendering them impractical for large-scale applications. Additionally, existing graph-based multi-view models struggle to adequately capture the inherent uncertainty characterized by ambiguous or overlapping clustering boundaries. To address these challenges, this paper proposes a multi-view fuzzy clustering method with anchor graph. Specifically, the proposed method learns a symmetric and doubly stochastic consensus similarity graph from multiple views and performs clustering directly on the learned consensus graph, thereby directly outputting clustering results. By imposing nonnegativity and row normalization constraints on the cluster indicator matrix, the proposed method can further reveal the underlying uncertain clustering structure. Furthermore, an iterative optimization algorithm with linear complexity is developed to solve the proposed model. Extensive experiments conducted on both synthetic and real-world benchmark datasets illustrate the effectiveness and efficiency of the proposed method against state-of-the-art models.