Neural Guided Constraint Logic Programming for Program Synthesis

By Lisa Zhang, Gregory Rosenblatt, Ethan Fetaya, Renjie Liao, William E. Byrd, M. Might, Raquel Urtasun, Richard S. Zemel. 2018

35 citations recorded by the source corpus.

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 this https URL We show that our neural-guided approach using constraints can synthesize programs faster in many cases, and importantly, can generalize to larger problems.

Subfields: Artificial Intelligence, Information Systems

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Sebastijan Dumancic
2. Angelika Kimmig
3. Robin Manhaeve
4. Luc De Raedt
5. Thomas Demeester
6. Vaishak Belle
7. Kristian Kersting

In Information Systems

1. Thomas Demeester
2. Luc De Raedt
3. Angelika Kimmig
4. Sebastijan Dumancic

Citations in the corpus

• DeepProbLog: Neural Probabilistic Logic Programming (2018, background): “[45] train a neural network to choose which candidate program to expand next while exploiting the constraints on the input-output examples, while Ellis et al.”