Learning Bayesian Network Structure from Incomplete Data Without Any Assumption

Abstract : Since most real-life data contain missing values, reasoning and learning with incomplete data has become crucial in data mining and machine learning. In particular, Bayesian networks are one machine learning technique that allows for reasoning with incomplete data, but training such networks on incomplete data may be a difficult task. Many methods were thus proposed to learn Bayesian network structure from incomplete data, based on multiple structure generation and scoring of their adequacy to the dataset. However, this kind of approaches may be time-consuming. Therefore we propose an efficient dependency analysis approach that uses a redefinition of probability calculation to take incomplete records into account while learning BN structure, without generating multiple possibilities. Some experiments on well-known benchmarks are described to show the validity of our proposal.
Type de document :
Communication dans un congrès
DASFAA'08: Database Systems for Advanced Applications, France. pp.408-423, 2008
Liste complète des métadonnées

https://hal-lirmm.ccsd.cnrs.fr/lirmm-00273888
Contributeur : Celine Fiot <>
Soumis le : mercredi 16 avril 2008 - 15:55:27
Dernière modification le : jeudi 24 mai 2018 - 15:59:23

Identifiants

  • HAL Id : lirmm-00273888, version 1

Collections

Citation

Céline Fiot, G. A. Putri Saptawati, Anne Laurent, Maguelonne Teisseire. Learning Bayesian Network Structure from Incomplete Data Without Any Assumption. DASFAA'08: Database Systems for Advanced Applications, France. pp.408-423, 2008. 〈lirmm-00273888〉

Partager

Métriques

Consultations de la notice

61