Learning to Solve Weighted Maximum Satisfiability with a Co-Training Architecture
This addresses the problem of efficiently solving complex weighted MaxSAT instances for applications in optimization and AI, representing an incremental improvement with novel architectural elements.
The paper tackles the weighted maximum satisfiability (MaxSAT) problem by proposing SplitGNN, a graph neural network-based approach with a co-training architecture, which achieves 3x faster convergence and outperforms modern heuristic solvers on larger, harder benchmarks.
Wepropose SplitGNN, a graph neural network (GNN)-based approach that learns to solve weighted maximum satisfiabil ity (MaxSAT) problem. SplitGNN incorporates a co-training architecture consisting of supervised message passing mech anism and unsupervised solution boosting layer. A new graph representation called edge-splitting factor graph is proposed to provide more structural information for learning, which is based on spanning tree generation and edge classification. To improve the solutions on challenging and weighted instances, we implement a GPU-accelerated layer applying efficient score calculation and relaxation-based optimization. Exper iments show that SplitGNN achieves 3* faster convergence and better predictions compared with other GNN-based ar chitectures. More notably, SplitGNN successfully finds solu tions that outperform modern heuristic MaxSAT solvers on much larger and harder weighted MaxSAT benchmarks, and demonstrates exceptional generalization abilities on diverse structural instances.