Neural Guided Constraint Logic Programming for Program Synthesis

Synthesizing programs using example input/outputs is a classic problem in artificial intelligence. We present a method for solving Programming By Example (PBE) problems by using a neural model to guide the search of a constraint logic programming system called miniKanren. Crucially, the neural model uses miniKanren's internal representation as input; miniKanren represents a PBE problem as recursive constraints imposed by the provided examples. We explore Recurrent Neural Network and Graph Neural Network models. We contribute a modified miniKanren, drivable by an external agent, available at https: //github. com/xuexue/neuralkanren. We show that our neural-guided approach using constraints can synthesize programs faster in many cases, and importantly, can generalize to larger problems.

Authors

• Lisa Zhang
• Gregory Rosenblatt University of Alabama at Birmingham
• Ethan Fetaya Bar Ilan University
• Renjie Liao
• William Byrd University of Alabama at Birmingham
• Matthew Might
• Raquel Urtasun
• Richard Zemel

Keywords

No keywords are indexed for this paper.