Learning To Solve Circuit-SAT: An Unsupervised Differentiable ApproachDownload PDF

Sep 27, 2018 (edited Dec 29, 2018)ICLR 2019 Conference Blind SubmissionReaders: Everyone
  • 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.
  • Keywords: Neuro-Symbolic Methods, Circuit Satisfiability, Neural SAT Solver, Graph Neural Networks
  • TL;DR: We propose a neural framework that can learn to solve the Circuit Satisfiability problem from (unlabeled) circuit instances.
11 Replies

Loading