Goal-Aware Neural SAT Solver

Modern neural networks obtain information about the problem and calculate the output solely from the input values. We argue that it is not always optimal, and the network's performance can be significantly improved by augmenting it with a query mechanism that allows the network at run time to make several solution trials and get feedback on the loss value on each trial. To demonstrate the capabilities of the query mechanism, we formulate an unsupervised (not depending on labels) loss function for Boolean Satisfiability Problem (SAT) and theoretically show that it allows the network to extract rich information about the problem. We then propose a neural SAT solver with a query mechanism called QuerySAT and show that it outperforms the neural baseline on a wide range of SAT tasks.

I. Introduction

Boolean Satisfiability Problem (SAT) is a significant NP-complete problem with numerous practical applications – product configuration, hardware verification, and software package management, to name a few. There is no single efficient algorithm that solves every SAT problem, but heuristics have been developed that are sufficient for solving many real-life tasks.