Cross-view Graph Matching Guided Anchor Alignment for Incomplete Multi-view Clustering

Abstract

Multi-view bipartite graph clustering methods select a few representative anchors and then establish a connection with original samples to generate the bipartite graphs for clustering, which maintains impressive performance while reducing time and space complexities. Despite their effectiveness in large-scale applications, few of them focus on cross-view anchor misalignment (CAM) problem. Then, misaligned anchor sets could destroy the consistent graph semantic structure of bipartite graphs across different views, thus hindering subsequent graph fusion and degrading the clustering performance. Especially when it comes to incomplete data, solving CAM problem becomes an intractable challenge. To address this challenge, we propose a novel Cross-view Graph Matching guided Anchor Alignment (CGMAA) for incomplete multi-view bipartite clustering. Specifically, we first propose a novel CGMAA framework to address CAM problem by predefining an anchor graph according to the prior anchor information. In addition, we unify CGMAA and bipartite graph tensor learning for incomplete multi-view clustering. Extensive experiments on ten complete/incomplete benchmark datasets demonstrate the effectiveness, efficiency, and superiority of the proposed CGMAA framework.