Relational decomposition for program synthesis
This work addresses program synthesis for AI and software engineering, offering a novel relational decomposition method that improves performance over existing approaches.
The paper tackled program synthesis by decomposing tasks into relational subtasks using input-output facts, and demonstrated that this approach outperforms standard representations and domain-specific methods on four challenging datasets.
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.