Multi-view Bipartite Graph Clustering with Collaborative Regularization

Despite the meaningful advancements in graph-based multi-view clustering methods, several challenges persist. Firstly, these methods often suffer from high computational costs, limiting their application to large-scale datasets. Secondly, direct derivation of bipartite graphs from raw data can introduce noise and interference factors. Lastly, many existing methods struggle to effectively capture both similarity and diversity information from bipartite graphs. To tackle these issues, this paper proposes a multi-view bipartite graph clustering method based on collaborative regularization (MBGC2R). Specifically, bipartite graphs are constructed using Gaussian kernel and feature decomposition techniques. Subsequently, collaborative regularization and adaptive learning are incorporated to capture diversity and similarity information within bipartite graphs, respectively. Experimental results across various multi-view datasets validate the superiority and efficiency of our proposed MBGC2R method.