Abstract : Networks are a commonly used mathematical model to describe the rich set of interactions between objects of interest. Many clustering methods have been developed in order to partition such structures, among which several rely on underlying probabilistic models, typically mixture models. The relevant hidden structure may however show overlapping groups in several applications. The Overlapping Stochastic Block Model (2011) has been developed to take this phenomenon into account. Nevertheless, the problem of the choice of the number of classes in the inference step is still open. To tackle this issue, we consider the proposed model in a Bayesian framework and develop a new criterion based on a non asymptotic approximation of the marginal log-likelihood. We describe how the criterion can be computed through a variational Bayes EM algorithm, and demonstrate its efficiency by running it on both simulated and real data.
Type de document :
Article dans une revue
Electronic journal of statistics , Shaker Heights, OH : Institute of Mathematical Statistics, 2014, 8, pp.762-794
https://hal.archives-ouvertes.fr/hal-00990277
Contributeur : Pierre Latouche <>
Soumis le : mardi 13 mai 2014 - 13:50:56
Dernière modification le : jeudi 9 février 2017 - 15:50:39
Pierre Latouche, Etienne Birmelé, Christophe Ambroise. Model Selection in Overlapping Stochastic Block Models. Electronic journal of statistics , Shaker Heights, OH : Institute of Mathematical Statistics, 2014, 8, pp.762-794. <hal-00990277>
