Lifted Variable Elimination for Probabilistic Logic Programming
arXiv:1405.3218 · doi:10.1017/S1471068414000283
Abstract
Lifted inference has been proposed for various probabilistic logical frameworks in order to compute the probability of queries in a time that depends on the size of the domains of the random variables rather than the number of instances. Even if various authors have underlined its importance for probabilistic logic programming (PLP), lifted inference has been applied up to now only to relational languages outside of logic programming. In this paper we adapt Generalized Counting First Order Variable Elimination (GC-FOVE) to the problem of computing the probability of queries to probabilistic logic programs under the distribution semantics. In particular, we extend the Prolog Factor Language (PFL) to include two new types of factors that are needed for representing ProbLog programs. These factors take into account the existing causal independence relationships among random variables and are managed by the extension to variable elimination proposed by Zhang and Poole for dealing with convergent variables and heterogeneous factors. Two new operators are added to GC-FOVE for treating heterogeneous factors. The resulting algorithm, called LP for Lifted Probabilistic Logic Programming, has been implemented by modifying the PFL implementation of GC-FOVE and tested on three benchmarks for lifted inference. A comparison with PITA and ProbLog2 shows the potential of the approach.
To appear in Theory and Practice of Logic Programming (TPLP). arXiv admin note: text overlap with arXiv:1402.0565 by other authors
References in corpus (5)
- The PITA System: Tabling and Answer Subsumption for Reasoning under Uncertainty
- Skolemization for Weighted First-Order Model Counting
- Lifted Variable Elimination: Decoupling the Operators from the Constraint Language
- Multiplicative Factorization of Noisy-Max
- Constraint Processing in Lifted Probabilistic Inference