Robust Subspace Clustering by Learning an Optimal Structured Bipartite Graph via Low-rank Representation

This paper addresses the subspace clustering problem based on low-rank representation. Combining with the idea of co-clustering, we proposed to learn an optimal structural bipartite graph. It's different with other classical subspace clustering methods which need spectral clustering as post-processing on the constructed graph to get the final result, our method can directly learn a structural graph with k connected components so that the different clusters are obtained easily. Furthermore, we introduce a regularization term of error matrix to our model which helps the proposed algorithm to be more effective to learn an optimal graph under the circumstances of various noise. Experimental results both on synthetic and benchmark datasets are presented to show the effectiveness and robustness of our model.