Learning logic programs by finding minimal unsatisfiable subprograms
Machine Learning
2024-01-30 v1 Logic in Computer Science
Abstract
The goal of inductive logic programming (ILP) is to search for a logic program that generalises training examples and background knowledge. We introduce an ILP approach that identifies minimal unsatisfiable subprograms (MUSPs). We show that finding MUSPs allows us to efficiently and soundly prune the search space. Our experiments on multiple domains, including program synthesis and game playing, show that our approach can reduce learning times by 99%.
Keywords
Cite
@article{arxiv.2401.16383,
title = {Learning logic programs by finding minimal unsatisfiable subprograms},
author = {Andrew Cropper and Céline Hocquette},
journal= {arXiv preprint arXiv:2401.16383},
year = {2024}
}