Poster
Learning a SAT Solver from Single-Bit Supervision
Daniel Selsam · Matthew Lamm · Benedikt B\"{u}nz · Percy Liang · Leonardo Moura · David L Dill
Great Hall BC #18
Keywords: [ graph neural network ] [ sat ] [ search ] [ theorem proving ] [ proof ]
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.
Live content is unavailable. Log in and register to view live content