Neural Guided Constraint Logic Programming for Program Synthesis

Reference. 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.

Cite

Cite as @zhang-2018-neural (helia, typst) · \cite{zhang-2018-neural} (LaTeX)

BibTeX

bibtex · 8 lines

@misc{zhang-2018-neural,
  author = {Lisa Zhang and Gregory Rosenblatt and Ethan Fetaya and Renjie Liao and William E. Byrd and Matthew Might and Raquel Urtasun and Richard Zemel},
  title = {Neural Guided Constraint Logic Programming for Program Synthesis},
  year = {2018},
  month = {9},
  eprint = {1809.02840},
  archiveprefix = {arXiv}
}

hayagriva YAML (typst)

yaml · 15 lines

zhang-2018-neural:
  type: misc
  title: Neural Guided Constraint Logic Programming for Program Synthesis
  author:
  - Zhang, Lisa
  - Rosenblatt, Gregory
  - Fetaya, Ethan
  - Liao, Renjie
  - Byrd, William E.
  - Might, Matthew
  - Urtasun, Raquel
  - Zemel, Richard
  date: 2018-09
  serial-number:
    arxiv: '1809.02840'

Download: zhang-2018-neural.bib · zhang-2018-neural.yml

Cites 31 works (0 here)

External (31)

Towards Synthesizing Complex Programs From Input-Output Examples (2018)
Learning a SAT Solver from Single-Bit Supervision (2018)
Tree-to-tree Neural Networks for Program Translation (2018)
Neural-Guided Deductive Search for Real-Time Program Synthesis from Examples (2018)
Learning to Represent Programs with Graphs (2018)
A unified approach to solving seven programming problems (functional pearl) (2017)
End-to-End Differentiable Proving (2017)
Deep API Programmer: Learning to Program with APIs (2017)
RobustFill: Neural Program Learning under Noisy I/O (2017)
Neuro-Symbolic Program Synthesis (2017)
Sampling for Bayesian Program Learning (2016)
DeepCoder: Learning to Write Programs (2016)
TerpreT: A Probabilistic Programming Language for Program Induction (2016)
Neural Programmer: Inducing Latent Programs with Gradient Descent (2016)
Neural Programmer-Interpreters (2016)
Gated Graph Sequence Neural Networks (2016)
Prioritized Experience Replay (2016)
Type-and-example-directed program synthesis (2015)
Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks (2015)
Synthesizing data structure transformations from input-output examples (2015)
Neural Turing Machines (2014)
Recursive Program Synthesis (2013)
µKanren: A minimal functional core for relational programming (2013)
miniKanren, live and untagged: Quine generation via relational interpreters (programming pearl) (2012)
Lecture 6.5—RmsProp: Divide the gradient by a running average of its recent magnitude (2012)
Automating string processing in spreadsheets using input-output examples (2011)
The Graph Neural Network Model (2009)
From variadic functions to variadic relations (2006)
Long Short-Term Memory (1997)
The Inference of Regular LISP Programs from Examples (1978)
A Methodology for LISP Program Construction from Examples (1977)