Large-Scale Clustering With Structured Optimal Bipartite Graph

The widespread arising of data size gives rise to the necessity of undertaking large-scale data clustering tasks. To do so, the bipartite graph theory is frequently applied to design a scalable algorithm, which depicts the relations between samples and a few anchors, instead of binding pairwise samples. However, the bipartite graphs and existing spectral embedding methods ignore the explicit cluster structure learning. They have to obtain cluster labels by using post-processing like K-Means. More than that, existing anchor-based approaches always acquire anchors by using centroids of K-Means or a few random samples, both of which are time-saving but performance-unstable. In this paper, we investigate the scalability, stableness and integration in large-scale graph clustering. We propose a cluster-structured graph learning model, thus obtaining a c-connected (c is the cluster number) bipartite graph and also getting discrete labels straightforward. Taking data feature or pairwise relation as a start point, we further design an initialization-independent anchor selection strategy. Experimental results reported for synthetic and real-world datasets demonstrate the proposed method outperforms its peers.