I. Introduction
Clustering divides the samples into disjoint groups such that the samples within the same group are highly similar to each other. As an unsupervised learning task, it has been widely applied in the research fields of machine learning, data mining, and computer vision [1]–[3]. For its important role, various clustering methods have been brought forward over the past decades, such as -means [4], support vector clustering [5], hierarchical clustering [6], multiview clustering [3], [7], and maximum margin clustering [8].