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.
| Original language | English |
|---|---|
| Pages (from-to) | 1737-1746 |
| Number of pages | 10 |
| Journal | Advances in Neural Information Processing Systems |
| Volume | 2018-December |
| State | Published - 2018 |
| Externally published | Yes |
| Event | 32nd Conference on Neural Information Processing Systems, NeurIPS 2018 - Montreal, Canada Duration: 2 Dec 2018 → 8 Dec 2018 |
Bibliographical note
Publisher Copyright:© 2018 Curran Associates Inc.All rights reserved.
Funding
Research reported in this publication was supported in part by the Natural Sciences and Engineering Research Council of Canada, and the National Center For Advancing Translational Sciences of the National Institutes of Health under Award Number OT2TR002517. R.L. was supported by Connaught International Scholarship. The content is solely the responsibility of the authors and does not necessarily represent the official views of the funding agencies.
| Funders | Funder number |
|---|---|
| Connaught International Scholarship | |
| National Institutes of Health | |
| National Center for Advancing Translational Sciences | |
| Natural Sciences and Engineering Research Council of Canada | OT2TR002517 |