Can Graph Neural Networks Learn to Solve MaxSAT Problem?
Liu, Minghao, Jia, Fuqi, Huang, Pei, Zhang, Fan, Sun, Yuchen, Cai, Shaowei, Ma, Feifei, Zhang, Jian
–arXiv.org Artificial Intelligence
With the rapid development of deep learning techniques, various recent work has tried to apply graph neural networks (GNNs) to solve NP-hard problems such as Boolean Satisfiability (SAT), which shows the potential in bridging the gap between machine learning and symbolic reasoning. However, the quality of solutions predicted by GNNs has not been well investigated in the literature. In this paper, we study the capability of GNNs in learning to solve Maximum Satisfiability (MaxSAT) problem, both from theoretical and practical perspectives. We build two kinds of GNN models to learn the solution of MaxSAT instances from benchmarks, and show that GNNs have attractive potential to solve MaxSAT problem through experimental evaluation. We also present a theoretical explanation of the effect that GNNs can learn to solve MaxSAT problem to some extent for the first time, based on the algorithmic alignment theory.
arXiv.org Artificial Intelligence
Nov-15-2021
- Country:
- North America
- United States
- Ohio (0.04)
- Oregon > Multnomah County
- Portland (0.04)
- New York > New York County
- New York City (0.04)
- Louisiana > Orleans Parish
- New Orleans (0.04)
- Hawaii > Honolulu County
- Honolulu (0.04)
- California
- Santa Clara County > San Jose (0.04)
- San Diego County > San Diego (0.04)
- Arizona > Maricopa County
- Phoenix (0.04)
- Canada
- Quebec > Montreal (0.04)
- British Columbia > Metro Vancouver Regional District
- Vancouver (0.04)
- United States
- Europe
- Spain > Catalonia
- Barcelona Province > Barcelona (0.04)
- Portugal > Lisbon
- Lisbon (0.04)
- Belgium > Wallonia
- Walloon Brabant > Louvain-la-Neuve (0.04)
- Spain > Catalonia
- Asia > China
- Africa > Ethiopia
- Addis Ababa > Addis Ababa (0.04)
- North America
- Genre:
- Research Report (1.00)
- Technology: