Neural Guided Constraint Logic Programming for Program Synthesis

September 08, 2018 · Entered Twilight · 🏛 Neural Information Processing Systems

"Last commit was 7.0 years ago (≥5 year threshold)"

Evidence collected by the PWNC Scanner

Repo contents: LICENSE, README.md, data, evalo.scm, gnn.py, gnn_grammar.py, helper.py, interact.py, interact.scm, lisp.py, mk.scm, query-outputs.scm, query.scm, rnn.py, rnn_grammar.py

Authors Lisa Zhang, Gregory Rosenblatt, Ethan Fetaya, Renjie Liao, William E. Byrd, Matthew Might, Raquel Urtasun, Richard Zemel arXiv ID 1809.02840 Category cs.LG: Machine Learning Cross-listed stat.ML Citations 33 Venue Neural Information Processing Systems Repository https://github.com/xuexue/neuralkanren ⭐ 93 Last Checked 2 months ago

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.