Fuzzy clustering approach for star-structured multi-type relational data

Recently, mining interrelated data among multiple types of objects attracts a lot of attention due to its importance in many real-world applications. Despite of extensive study on fuzzy clustering of vector space data and homogeneous relational data, very limited exploration has been made on fuzzy clustering of relational data involving several object types. In this paper, we propose FC-SMR, a fuzzy approach for clustering star-structured multi-type relational data, where the central type is related to multiple attribute types. In FC-SMR, objects of the central type are clustered based on the rankings of objects of different attribute types. We formulate the clustering problem as a constrained maximization problem and give an efficient algorithm for finding local solutions of the defined objective function. Experimental studies conducted on real-world document data show the effectiveness of the new approach.