Learning Logic Programs by Discovering Where Not to Search

Abstract

The goal of inductive logic programming (ILP) is to search for a hypothesis that generalises training examples and background knowledge (BK). To improve performance, we introduce an approach that, before searching for a hypothesis, first discovers "where not to search". We use given BK to discover constraints on hypotheses, such as that a number cannot be both even and odd. We use the constraints to bootstrap a constraint-driven ILP system. Our experiments on multiple domains (including program synthesis and inductive general game playing) show that our approach can (i) substantially reduce learning times by up to 97%, and (ii) can scale to domains with millions of facts.

Cite

Text

Cropper and Hocquette. "Learning Logic Programs by Discovering Where Not to Search." AAAI Conference on Artificial Intelligence, 2023. doi:10.1609/AAAI.V37I5.25774

Markdown

[Cropper and Hocquette. "Learning Logic Programs by Discovering Where Not to Search." AAAI Conference on Artificial Intelligence, 2023.](https://mlanthology.org/aaai/2023/cropper2023aaai-learning/) doi:10.1609/AAAI.V37I5.25774

BibTeX

@inproceedings{cropper2023aaai-learning,
  title     = {{Learning Logic Programs by Discovering Where Not to Search}},
  author    = {Cropper, Andrew and Hocquette, Céline},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2023},
  pages     = {6289-6296},
  doi       = {10.1609/AAAI.V37I5.25774},
  url       = {https://mlanthology.org/aaai/2023/cropper2023aaai-learning/}
}