Learning a SAT Solver from Single-Bit Supervision
Abstract
We present NeuroSAT, a message passing neural network that learns to solve SAT problems after only being trained as a classifier to predict satisfiability. Although it is not competitive with state-of-the-art SAT solvers, NeuroSAT can solve problems that are substantially larger and more difficult than it ever saw during training by simply running for more iterations. Moreover, NeuroSAT generalizes to novel distributions; after training only on random SAT problems, at test time it can solve SAT problems encoding graph coloring, clique detection, dominating set, and vertex cover problems, all on a range of distributions over small random graphs.
Cite
Text
Selsam et al. "Learning a SAT Solver from Single-Bit Supervision." International Conference on Learning Representations, 2019.Markdown
[Selsam et al. "Learning a SAT Solver from Single-Bit Supervision." International Conference on Learning Representations, 2019.](https://mlanthology.org/iclr/2019/selsam2019iclr-learning/)BibTeX
@inproceedings{selsam2019iclr-learning,
title = {{Learning a SAT Solver from Single-Bit Supervision}},
author = {Selsam, Daniel and Lamm, Matthew and B\"{u}nz, Benedikt and Liang, Percy and de Moura, Leonardo and Dill, David L.},
booktitle = {International Conference on Learning Representations},
year = {2019},
url = {https://mlanthology.org/iclr/2019/selsam2019iclr-learning/}
}