Learning To Solve Circuit-SAT: An Unsupervised Differentiable Approach
Saeed Amizadeh, Sergiy Matusevych, Markus Weimer
Abstract
Recent efforts to combine Representation Learning with Formal Methods, commonly known as the Neuro-Symbolic Methods, have given rise to a new trend of applying rich neural architectures to solve classical combinatorial optimization problems. In this paper, we propose a neural framework that can learn to solve the Circuit Satisfiability problem. Our framework is built upon two fundamental contributions: a rich embedding architecture that encodes the problem structure and an end-to-end differentiable training procedure that mimics Reinforcement Learning and trains the model directly toward solving the SAT problem. The experimental results show the superior out-of-sample generalization performance of our framework compared to the recently developed NeuroSAT method.
BibTeX
@inproceedings{
amizadeh2018learning,
title={Learning To Solve Circuit-{SAT}: An Unsupervised Differentiable Approach},
author={Saeed Amizadeh and Sergiy Matusevych and Markus Weimer},
booktitle={International Conference on Learning Representations},
year={2019},
url={https://openreview.net/forum?id=BJxgz2R9t7},
}