Learning a SAT Solver from Single-Bit Supervision

02/11/2018
by   Daniel Selsam, et al.
0

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.

READ FULL TEXT

page 4

page 7

09/26/2019

Improving SAT Solver Heuristics with Graph Networks and Reinforcement Learning

We present GQSAT, a branching heuristic in a Boolean SAT solver trained ...
09/04/2020

NNgSAT: Neural Network guided SAT Attack on Logic Locked Complex Structures

The globalization of the IC supply chain has raised many security threat...
06/14/2019

Effective problem solving using SAT solvers

In this article we demonstrate how to solve a variety of problems and pu...
01/15/2014

Relaxed Survey Propagation for The Weighted Maximum Satisfiability Problem

The survey propagation (SP) algorithm has been shown to work well on lar...
03/12/2019

NeuroCore: Guiding High-Performance SAT Solvers with Unsat-Core Predictions

The NeuroSAT neural network architecture was introduced for predicting p...
03/12/2019

Guiding High-Performance SAT Solvers with Unsat-Core Predictions

The NeuroSAT neural network architecture was recently introduced for pre...
07/06/2020

Enhancing SAT solvers with glue variable predictions

Modern SAT solvers routinely operate at scales that make it impractical ...

Code Repositories

neurosat

NeuroSAT: Learning a SAT Solver from Single-Bit Supervision


view repo