Stochastic blockmodels for exchangeable collections of networks.
Reyes, P. E. and Rodriguez, A.
Bayesian Analysis. Submitted 2016.
We construct a novel class of stochastic blockmodels using Bayesian nonparametric mixtures. These models allow us to jointly estimate the structure of multiple networks and explicitly compare the community structures underlying them while capturing some of their realistic properties. Inference is carried out using MCMC algorithms that incorporate sequentially allocated split-merge steps to improve mixing. The models are illustrated using a simulation study and a variety of real-life examples.
KEYWORDS: Dependent Dirichlet process, Nonparametric Bayes, Networks.