TP-Compilation for inference in probabilistic logic programs

Vlasselaer, Jonas, Van den Broeck, Guy, Kimmig, Angelika ORCID: https://orcid.org/0000-0002-6742-4057, Meert, Wannes and De Raedt, Luc 2016. TP-Compilation for inference in probabilistic logic programs. International Journal of Approximate Reasoning 78 , pp. 15-32. 10.1016/j.ijar.2016.06.009

Preview

PDF - Accepted Post-Print Version Download (601kB) | Preview

Abstract

We propose TP -compilation, a new inference technique for probabilistic logic programs that is based on forward reasoning. TP -compilation proceeds incrementally in that it interleaves the knowledge compilation step for weighted model counting with forward reasoning on the logic program. This leads to a novel anytime algorithm that provides hard bounds on the inferred probabilities. The main difference with existing inference techniques for probabilistic logic programs is that these are a sequence of isolated transformations. Typically, these transformations include conversion of the ground program into an equivalent propositional formula and compilation of this formula into a more tractable target representation for weighted model counting. An empirical evaluation shows that TP -compilation effectively handles larger instances of complex or cyclic real-world problems than current sequential approaches, both for exact and anytime approximate inference. Furthermore, we show that TP -compilation is conducive to inference in dynamic domains as it supports efficient updates to the compiled model.

Item Type:	Article
Date Type:	Publication
Status:	Published
Schools:	Computer Science & Informatics
Publisher:	Elsevier
ISSN:	0888-613X
Date of First Compliant Deposit:	20 November 2017
Date of Acceptance:	9 June 2016
Last Modified:	27 Nov 2024 10:30
URI:	https://orca.cardiff.ac.uk/id/eprint/106734

Citation Data

Cited 20 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item