On the Expressive Power of GNNs for Boolean Satisfiability

ICLR 2026 Conference Submission20096 Authors

Keywords: SAT, GNN, Weisfeiler-Leman, expressivity

TL;DR: We study the expressive power of GNNs for SAT solving, showing that even the full Weisfeiler-Leman hierarchy cannot distinguish satisfiable instances from unsatisfiable, and that industrial instances often require more expressivity than random ones.

Abstract: Machine learning approaches to solving Boolean Satisfiability (SAT) aim to replace handcrafted heuristics with learning-based models. Graph Neural Networks have emerged as the main architecture for SAT solving, due to the natural graph representation of Boolean formulas. We analyze the expressive power of GNNs for SAT solving through the lens of the Weisfeiler-Leman (WL) test. As our main result, we prove that the full WL hierarchy cannot, in general, distinguish between satisfiable and unsatisfiable instances. We show that indistinguishability under higher-order WL carries over to practical limitations for WL-bounded solvers that set variables sequentially. We further study the expressivity required for several important families of SAT instances, including regular, random and planar instances. To quantify expressivity needs in practice, we conduct experiments on random instances from the G4SAT benchmark and industrial instances from the 2024 SAT competition. Our results suggest that while random instances are largely distinguishable, industrial instances often require more expressivity to predict a satisfying assignment.

Primary Area: learning on graphs and other geometries & topologies

Submission Number: 20096