Learning Logic Programs Though Divide, Constrain, and Conquer
DOI:
https://doi.org/10.1609/aaai.v36i6.20596Keywords:
Machine Learning (ML), Knowledge Representation And Reasoning (KRR), Constraint Satisfaction And Optimization (CSO)Abstract
We introduce an inductive logic programming approach that combines classical divide-and-conquer search with modern constraint-driven search. Our anytime approach can learn optimal, recursive, and large programs and supports predicate invention. Our experiments on three domains (classification, inductive general game playing, and program synthesis) show that our approach can increase predictive accuracies and reduce learning times.Downloads
Published
2022-06-28
How to Cite
Cropper, A. (2022). Learning Logic Programs Though Divide, Constrain, and Conquer. Proceedings of the AAAI Conference on Artificial Intelligence, 36(6), 6446-6453. https://doi.org/10.1609/aaai.v36i6.20596
Issue
Section
AAAI Technical Track on Machine Learning I