---
title: "Relational Decomposition for Program Synthesis"
authors:
  - "Céline Hocquette"
  - "Andrew Cropper"
doi: "10.24963/ijcai.2025/504"
url: "https://ijcai.org/proceedings/2025/504"
pdf: "https://ijcai.org/proceedings/2025/0504.pdf"
venue: "Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"
year: 2025
pages: "4526-4534"
track: "Main Track"
keywords:
  - "Knowledge Representation and Reasoning: KRR: Learning and reasoning"
  - "Knowledge Representation and Reasoning: KRR: Logic programming"
---

# Relational Decomposition for Program Synthesis

Céline Hocquette, Andrew Cropper

*Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence*, pages 4526-4534. DOI: [10.24963/ijcai.2025/504](https://doi.org/10.24963/ijcai.2025/504)

## 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.