|
Abstract:
|
A network clustering algorithm is useful for understanding the structure of network data. Clustering methods usually group vertices based on a certain similarity/distance measure, such that vertices assigned in the same clusters are more closely related than vertices in different clusters. Therefore, network clustering can be formulated as an optimal problem to maximize the contrast of within-cluster and between-cluster closeness. However, most of the existing clustering methods are greedy algorithm. In this poster, we explore the usage of a cross-entropy Monte Carlo method for solving such a combinatorial problem. Instead of placing a discrete uniform distribution on all the potential solutions, an iterative importance sampling technique is utilized “to slowly tighten the net” to place most distributional mass on the optimal community structure and its neighbors. Simulation studies were conducted to assess the performance of the method.
|
