Semisupervised Fuzzy Clustering With Partition Information of Subsets
Jian-Ping Mei · IEEE Transactions on Fuzzy Systems · 2018
Pairwise constraint is a type of side information that is widely considered in existing semisupervised clustering approaches. In this paper, we explore a new form of supervision for clustering. We consider the partition results of a number of subsets as additional information to assist clustering. Compared to the pairwise constraint, which only involves the “must-link” or “cannot-link” relationship of two objects, the partition of a subset of objects provides information about the group structure of more objects and hence can possibly serve as a more effective form of supervision for clustering. In this paper, we instantiate the idea of clustering with subset partitions under the fuzzy clustering framework for document categorization. The proposed fuzzy clustering approach is formulated to learn from the partition of subsets and has the ability to handle high-dimensional document data. Specifically, the partition results of subsets are collectively transformed into pairwise relationships, based on which a penalty term is constructed and incorporated into a cosine-distance-based fuzzy c-means approach. The experimental results on benchmark data sets demonstrate the effectiveness of the proposed approach for a semisupervised document clustering.