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.



There are no comments yet.


page 4

page 7

Code Repositories


NeuroSAT: Learning a SAT Solver from Single-Bit Supervision

view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.