Learning to Combine Per-Example Solutions for Neural Program Synthesis

Disha Shrivastava, Hugo Larochelle, Daniel Tarlow

Keywords: program synthesis, neural program synthesis, program induction, program understanding and generation, multi-head attention, programming by example

Abstract: The goal of program synthesis from examples is to find a computer program that is consistent with a given set of input-output examples. Most learning-based approaches try to find a program that satisfies all examples at once. Our work, by contrast, considers an approach that breaks the problem into two stages: (a) find programs that satisfy only one example, and (b) leverage these per-example solutions to yield a program that satisfies all examples. We introduce the Cross Aggregator neural network module based on a multi-head attention mechanism that learns to combine the cues present in these per-example solutions to synthesize a global solution. Evaluation across programs of different lengths and under two different experimental settings reveal that when given the same time budget, our technique significantly improves the success rate over PCCoder [Zohar et. al 2018] and other ablation baselines.

Code Of Conduct: I certify that all co-authors of this work have read and commit to adhering to the NeurIPS Statement on Ethics, Fairness, Inclusivity, and Code of Conduct.

TL;DR: We propose a technique for neural program synthesis based on: (a) finding separate solutions for each input-output example, and (b) learning to combine them to satisfy all examples.

Code: https://github.com/shrivastavadisha/N-PEPS

Community Implementations: [ 2 code implementations](https://www.catalyzex.com/paper/arxiv:2106.07175/code)