Saved in:
Bibliographic Details
Main Authors: Wan, Kaidi, Liu, Minghao, Lai, Yong
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.19544
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914169842827264
author Wan, Kaidi
Liu, Minghao
Lai, Yong
author_facet Wan, Kaidi
Liu, Minghao
Lai, Yong
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_19544
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learning to Solve Weighted Maximum Satisfiability with a Co-Training Architecture
Wan, Kaidi
Liu, Minghao
Lai, Yong
Machine Learning
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.
title Learning to Solve Weighted Maximum Satisfiability with a Co-Training Architecture
topic Machine Learning
url https://arxiv.org/abs/2511.19544