Neural Program Synthesis with Query

TL;DR

This paper introduces a query-based neural program synthesis framework that automatically generates informative input-output examples to improve program learning, outperforming traditional methods relying on well-designed examples.

Contribution

It proposes a novel query neural network framework utilizing mutual information and a functional space to generate effective input-output examples for program synthesis.

Findings

The framework effectively generates informative examples that improve synthesis performance.

It outperforms methods using manually designed input-output examples.

Demonstrates strong generalization on Karel and list processing tasks.

Abstract

Aiming to find a program satisfying the user intent given input-output examples, program synthesis has attracted increasing interest in the area of machine learning. Despite the promising performance of existing methods, most of their success comes from the privileged information of well-designed input-output examples. However, providing such input-output examples is unrealistic because it requires the users to have the ability to describe the underlying program with a few input-output examples under the training distribution. In this work, we propose a query-based framework that trains a query neural network to generate informative input-output examples automatically and interactively from a large query space. The quality of the query depends on the amount of the mutual information between the query and the corresponding program, which can guide the optimization of the query framework. To estimate the mutual information more accurately, we introduce the functional space (F-space) which models the relevance between the input-output examples and the programs in a differentiable way. We evaluate the effectiveness and generalization of the proposed query-based framework on the Karel task and the list processing task. Experimental results show that the query-based framework can generate informative input-output examples which achieve and even outperform well-designed input-output examples.