Fast Bayesian Network Structure Learning using Quasi-determinism Screening

Thibaud Rahier 1, 2 Sylvain Marié 1 Stéphane Girard 2 Florence Forbes 2
2 MISTIS - Modelling and Inference of Complex and Structured Stochastic Systems
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : 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.
Type de document :
Pré-publication, Document de travail
2018
Liste complète des métadonnées

Littérature citée [36 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01691217
Contributeur : Thibaud Rahier <>
Soumis le : mercredi 24 janvier 2018 - 15:09:25
Dernière modification le : lundi 29 janvier 2018 - 15:41:21

Fichier

FastBNSLWithQDS.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01691217, version 2

Collections

Citation

Thibaud Rahier, Sylvain Marié, Stéphane Girard, Florence Forbes. Fast Bayesian Network Structure Learning using Quasi-determinism Screening. 2018. 〈hal-01691217v2〉

Partager

Métriques

Consultations de la notice

135

Téléchargements de fichiers

56