Distributed MCMC inference for Bayesian Non-Parametric Latent Block Model

Reda Khoufache (1) , Anisse Belhadj (1) , Hanene Azzag (2) , Mustapha Lebbah (1)

1 DAVID - Données et algorithmes pour une ville intelligente et durable - DAVID
2 LIPN - Laboratoire d'Informatique de Paris-Nord

In this paper, we introduce a novel Distributed Markov Chain Monte Carlo (MCMC) inference method for the Bayesian Non-Parametric Latent Block Model (DisNPLBM), employing the Master/Worker architecture. Our non-parametric co-clustering algorithm divides observations and features into partitions using latent multivariate Gaussian block distributions. The rows are evenly distributed among workers, which exclusively communicate with the master and not among themselves. DisNPLBM demonstrates its impact on cluster labeling accuracy and execution times through experimental results. Moreover, we present a real-use case applying our approach to co-cluster gene expression data. The code source is publicly available at https://github.com/redakhoufache/Distributed-NPLBM.

Mots clés: Co-clustering; Bayesian non-parametric; Distributed computing

Domaines: Machine Learning [stat.ML]

Reda Khoufache, Anisse Belhadj, Hanene Azzag, Mustapha Lebbah. Distributed MCMC inference for Bayesian Non-Parametric Latent Block Model. Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD), May 2024, Taipei, Taiwan. ⟨hal-04457575⟩