Weighted Model Counting with Conditional Weights for Bayesian Networks

Paulius Dilkas, Vaishak Belle

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

Weighted model counting (WMC) has emerged as the unifying inference mechanism across many (probabilistic) domains. Encoding an inference problem as an instance of WMC typically necessitates adding extra literals and clauses. This is partly so because the predominant definition of WMC assigns weights to models based on weights on literals, and this severely restricts what probability distributions can be represented. We develop a measure-theoretic perspective on WMC and propose a way to encode conditional weights on literals analogously to conditional probabilities. This representation can be as succinct as standardWMC with weights on literals but can also expand as needed to represent probability distributions with less structure. To demonstrate the performance benefits of conditional weights over the addition of extra literals, we develop a new WMC encoding for Bayesian networks and adapt a state-of-the-art WMC algorithm ADDMC to the new format. Our experiments show that the new encoding significantly improves the performance of the algorithm on most benchmark instances.
Original languageEnglish
Title of host publicationProceedings of the the 37th Conference on Uncertainty in Artificial Intelligence (UAI 2021)
EditorsCassio de Campos, Marloes H. Maathuis
Place of PublicationNew York, United States
PublisherPMLR
Pages386-396
Number of pages11
Volume161
Publication statusPublished - 27 Jul 2021
Event37th Conference on Uncertainty in Artificial Intelligence - Online
Duration: 27 Jul 202130 Jul 2021
https://www.auai.org/uai2021/

Publication series

NameProceedings of Machine Learning Research
PublisherPMLR
Volume161
ISSN (Electronic)2640-3498

Conference

Conference37th Conference on Uncertainty in Artificial Intelligence
Abbreviated titleUAI 2021
Period27/07/2130/07/21
Internet address

Fingerprint

Dive into the research topics of 'Weighted Model Counting with Conditional Weights for Bayesian Networks'. Together they form a unique fingerprint.

Cite this