Data clustering with a relational push-pull model

Relational data clustering is the task of grouping data ob-jects together when both features and relations between ob-jects are present. We present a new generative model for relational data in which relations between objects can have either a binding or separating effect. For example, with a group of students separated into gender clusters, a “dating” relation would appear most frequently between the clusters, but a “roommate ” relation would appear more often within clusters. In visualizing these relations, one can imagine that the “dating ” relation effectively pushes clusters apart, while the “roommate ” relation pulls clusters into tighter forma-tions. We use simulated annealing to search for optimal values of the unknown model parameters, where the objec-tive function is a Bayesian score derived from the generative model. Experiments on synthetic data demonstrate the ro-bustness of the model