Neural guided constraint logic programming for program synthesis

Academic Article

Abstract

  • 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

    Pubmed Id

  • 8460732
  • Author List

  • Zhang L; Rosenblatt G; Fetaya E; Liao R; Byrd WE; Might M; Urtasun R; Zemel R
  • Start Page

  • 1737
  • End Page

  • 1746
  • Volume

  • 2018-December