AINeutralarXiv – CS AI · Mar 57/10
🧠
A Geometric Perspective on the Difficulties of Learning GNN-based SAT Solvers
Researchers explain why Graph Neural Networks (GNNs) struggle with complex Boolean Satisfiability Problems (SATs) through geometric analysis using graph Ricci Curvature. They prove that harder SAT instances have more negative curvature, creating connectivity bottlenecks that prevent GNNs from effectively processing long-range dependencies.