We propose a scalable algorithm for model selection in sigmoid belief networks (SBNs), based on the factorized asymptotic Bayesian (FAB) framework. We derive the corresponding generalized factorized information criterion (gFIC) for the SBN, which is proven to be statistically consistent with the marginal log-likelihood. To capture the dependencies within hidden variables in SBNs, a recognition network is employed to model the variational distribution. The resulting algorithm, which we call FABIA, can simultaneously execute both model selection and inference by maximizing the lower bound of gFIC. On both synthetic and real data, our experiments suggest that FABIA, when compared to state-of-the-art algorithms for learning SBNs, $(i)$ produces a more concise model, thus enabling faster testing; $(ii)$ improves predictive performance; $(iii)$ accelerates convergence; and $(iv)$ prevents overfitting.

With a growing need to understand large-scale networks, factorial relational models, such as binary matrix factorization models (BMFs), have become important in many applications. Although BMFs have a natural capability to uncover overlapping group structures behind network data, existing inference techniques have issues of either high computational cost or lack of model selection capability, and this limits their applicability. For scalable model selection of BMFs, this paper proposes stochastic factorized asymptotic Bayesian (sFAB) inference that combines concepts in two recently-developed techniques: stochastic variational inference (SVI) and FAB inference. sFAB is a highly-efficient algorithm, having both scalability and an inherent model selection capability in a single inference framework. Empirical results show the superiority of sFAB/BMF in both accuracy and scalability over state-of-the-art inference methods for overlapping relational models.

To build up spontaneous conversation, it is important to select topics without a feeling of strangeness. When someone notices others are not interested in a topic, he/she tries to find a new topic. Then, he/she thinks of viewpoints of the conversation and selects a topic associated with the current topic from the viewpoints. To automate viewpoint-based topic selection, we present 5W viewpoint associative topic search. The method estimates the weights of 5W viewpoints (who, what, where, when and why) from conversation, to use an appropriate similarity to search for the next topic.