Sparse neighbor constrained co-clustering via category consistency learning

Abstract

Clustering has long been an enduring and promising task in machine learning. However, developed one-side clustering is still insufficient to explore the context of data, such as texts and genes. Hence, developing two-way clustering has drawn more attention in recent years, which tends to cluster samples and features simultaneously. This paper proposes a sparse neighbor constrained co-clustering via category consistency learning, for alleviating the misclassification of close points. Following an additional observation, samples often fall into the same category as their neighbors, as do features. Accordingly, the co-clustering problem is formulated as nonnegative matrix tri-factorization appended dual regularizers, considering coherence between data affinity and label assignment. Then, a multiplicative alternating scheme is raised for objective optimization, whose convergence and correctness are theoretically guaranteed. Furthermore, the proposed approach is validated on six datasets using three evaluation metrics, whose parameter sensitivity is analyzed as well. Finally, comprehensive experiments show that our algorithm is competitive against existing ones.