A0849
Title: Extended stochastic block models via Gibbs-type priors
Authors: Daniele Durante - Bocconi University (Italy) [presenting]
Abstract: Reliably learning group structures in network data is challenging in several applications. The focus is on converting networks that encode relationships among criminals. Such data exhibit a complex combination of an unknown number of core-periphery, assortative and disassortative structures that may unveil the architectures of the criminal organization. The coexistence of these noisy block patterns limits the reliability of routine community detection algorithms and requires extensions of model-based solutions to realistically characterize the node partition process, incorporate node attributes, and provide improved inference strategies. To cover these gaps, we will present a new class of extended stochastic block models (ESBM) that infer groups of nodes having common connectivity patterns via Gibbs-type priors on the partition process. This choice encompasses many realistic priors for criminal networks, covering solutions with fixed, random and infinite number of groups, and facilitates the inclusion of node attributes in a principled manner. Among the new alternatives in this class, we will focus on the Gnedin process as a realistic prior that allows the number of groups to be finite, random and subject to a reinforcement process coherent with criminal networks. A collapsed Gibbs sampler is proposed for the whole ESBM class, and improved inference strategies are outlined. The ESBM performance is illustrated in simulations and in an application to an Italian mafia network.
