Learning Logic Programs by Discovering Higher-Order Abstractions

Céline Hocquette; Sebastijan Dumancic; Andrew Cropper

IJCAI 2024poster5 citations

Learning Logic Programs by Discovering Higher-Order Abstractions

Céline Hocquette, Sebastijan Dumancic, Andrew Cropper

Abstract

We introduce the higher-order refactoring problem, where the goal is to compress a logic program by discovering higher-order abstractions, such as map, filter, and fold. We implement our approach in Stevie, which formulates the refactoring problem as a constraint optimisation problem. Our experiments on multiple domains, including program synthesis and visual reasoning, show that refactoring can improve the learning performance of an inductive logic programming system, specifically improving predictive accuracies by 27% and reducing learning times by 47%. We also show that Stevie can discover abstractions that transfer to multiple domains.

Knowledge Representation and Reasoning: KRR: Logic programmingMachine Learning: ML: Symbolic methods

BibTeX

@inproceedings{ijcai2024p379,
  title     = {Learning Logic Programs by Discovering Higher-Order Abstractions},
  author    = {Hocquette, Céline and Dumancic, Sebastijan and Cropper, Andrew},
  booktitle = {Proceedings of the Thirty-Third International Joint Conference on
               Artificial Intelligence, {IJCAI-24}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Kate Larson},
  pages     = {3421--3429},
  year      = {2024},
  month     = {8},
  note      = {Main Track},
  doi       = {10.24963/ijcai.2024/379},
  url       = {https://doi.org/10.24963/ijcai.2024/379},
}