A0503
Title: A dynamic latent block model for co-clustering of zero-inflated count data streams
Authors: Giulia Marchello - Universite Cote dAzur, Inria (France) [presenting]
Marco Corneli - Universite Cote d Azur (France)
Charles Bouveyron - INRIA, Universite Cote d'Azur (France)
Abstract: The simultaneous clustering of observations and features of data sets (known as co-clustering) has recently emerged as a central machine learning application to summarize massive data sets. However, most existing models focus on continuous data in stationary scenarios, where cluster assignments do not evolve over time. A novel latent block model is introduced for the dynamic co-clustering of count data streams with high sparsity. To properly model this type of data, we assume that the observations follow a time and block-dependent mixture of zero-inflated Poisson distributions, which combines two independent processes: a dynamic mixture of Poisson distributions and a time-dependent sparsity process. To model and detect abrupt changes in the dynamics of both clusters' memberships and data sparsity, the mixing and sparsity proportions are modeled through systems of ordinary differential equations. The model inference relies on an original variational procedure whose maximization step trains recurrent neural networks in order to solve the dynamical systems. Numerical experiments on simulated data sets demonstrate the effectiveness of the proposed methodology.
