Fast Bayesian Network Structure Learning using Quasi-determinism Screening

Thibaud Rahier (1, 2, 3) , Sylvain Marié (2) , Stéphane Girard (1, 3) , Florence Forbes (1, 3)

1 Inria - Institut National de Recherche en Informatique et en Automatique
2 SE - Schneider Electric
3 MISTIS - Modelling and Inference of Complex and Structured Stochastic Systems

Learning the structure of Bayesian Networks from data is a NP-Hard problem that involves an optimization task on a super-exponential sized space. In this work, we show that in most real life datasets, a number of the arcs contained in the final structure can be pre-screened at low computational cost with a limited impact on the global graph score. We formalize the identification of these arcs via the notion of quasi-determinism, and propose an algorithm exploiting the screening that reduces the structure learning on a subset of the original variables. We show, on diverse benchmark datasets, that this algorithm exhibits a significant decrease in computational time for little decrease in performance score.

Domaines: Probabilités [math.PR]; Autres [stat.ML]; Machine Learning [stat.ML]

Thibaud Rahier, Sylvain Marié, Stéphane Girard, Florence Forbes. Fast Bayesian Network Structure Learning using Quasi-determinism Screening. 2018. ⟨hal-01691217v1⟩