基于 GNN 的 SAT 求解中的变量依赖问题解决（英文版）

英文标题：Addressing Variable Dependency in GNN-based SAT Solving中文摘要：AsymSAT 是一种基于 GNN 的架构，能够扩展 GNN-based 方法的解题能力，改善 SAT 问题求解的性能，并通过使用生成的相关预测来维护变量之间的依赖关系。英文摘要：Boolean satisfiability problem (SAT) is fundamental to many applications.Existing works have used graph neural networks (GNNs) for (approximate) SATsolving. Typical GNN-based end-to-end SAT solvers predict SAT solutionsconcurrently. We show that for a group of symmetric SAT problems, theconcurrent prediction is guaranteed to produce a wrong an