CNNSAT: Fast, Accurate Boolean Satisfiability using Convolutional Neural Networks

Yu Wang, Fengjuan Gao, Amin Alipour, Linzhang Wang, Xuandong Li, Zhendong Su

Abstract:

Boolean satisfiability (SAT) is one of the most well-known NP-complete
problems and has been extensively studied. State-of-the-art solvers
exist and have found a wide range of applications. However, they still
do not scale well to formulas with hundreds of variables. To tackle
this fundamental scalability challenge, we introduce CNNSAT, a fast
and accurate statistical decision procedure for SAT based on
convolutional neural networks. CNNSAT's effectiveness is due to a
precise and compact representation of Boolean
formulas. On both real and synthetic formulas, CNNSAT is highly
accurate and orders of magnitude faster than the
state-of-the-art solver Z3. We also describe how to extend CNNSAT to
predict satisfying assignments when it predicts a formula to be
satisfiable.

Keywords: Convolutional Neural Networks, Boolean satisfiability problem, Satisfiability modulo theories

TL;DR: We introduce CNNSAT, a fast and accurate statistical decision procedure for SAT based on convolutional neural networks.