Relational Decomposition for Program Synthesis
Abstract
We introduce a relational approach to program synthesis. The key idea is to decompose synthesis tasks into simpler relational synthesis subtasks. Specifically, our representation decomposes a training input-output example into sets of input and output facts respectively. We then learn relations between the input and output facts. We demonstrate our approach using an off-the-shelf inductive logic programming (ILP) system on four challenging synthesis datasets. Our results show that (i) our representation can outperform a standard one, and (ii) an off-the-shelf ILP system with our representation can outperform domain-specific approaches.
Cite
Text
Hocquette and Cropper. "Relational Decomposition for Program Synthesis." International Joint Conference on Artificial Intelligence, 2025. doi:10.24963/IJCAI.2025/504Markdown
[Hocquette and Cropper. "Relational Decomposition for Program Synthesis." International Joint Conference on Artificial Intelligence, 2025.](https://mlanthology.org/ijcai/2025/hocquette2025ijcai-relational/) doi:10.24963/IJCAI.2025/504BibTeX
@inproceedings{hocquette2025ijcai-relational,
title = {{Relational Decomposition for Program Synthesis}},
author = {Hocquette, Céline and Cropper, Andrew},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2025},
pages = {4526-4534},
doi = {10.24963/IJCAI.2025/504},
url = {https://mlanthology.org/ijcai/2025/hocquette2025ijcai-relational/}
}