Relational decomposition for program synthesis

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hocquette, Céline, Cropper, Andrew
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910996931543040
author Hocquette, Céline
Cropper, Andrew
author_facet Hocquette, Céline
Cropper, Andrew
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2408_12212
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Relational decomposition for program synthesis
Hocquette, Céline
Cropper, Andrew
Artificial Intelligence
Machine Learning
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.
title Relational decomposition for program synthesis
topic Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2408.12212