Frontiers in Artificial Intelligence · 2021 · 33 citations · 26 references
ComputingComputer ScienceAlgorithmsMachine LearningOptimizationCombinatorial OptimizationConstrained OptimizationConstraint SatisfactionConstraint SolvingGraph AlgorithmsGraph-based LearningConstraint OptimizationConstraint Optimization ProblemsGraph Neural NetworksGraph Optimization
Many combinatorial optimization problems can be phrased in the language of constraint satisfaction problems. We introduce a graph neural network architecture for solving such optimization problems. The architecture is generic; it works for all binary constraint satisfaction problems. Training is unsupervised, and it is sufficient to train on relatively small instances; the resulting networks perform well on much larger instances (at least 10-times larger). We experimentally evaluate our approach for a variety of problems, including Maximum Cut and Maximum Independent Set. Despite being generic, we show that our approach matches or surpasses most greedy and semi-definite programming based algorithms and sometimes even outperforms state-of-the-art heuristics for the specific problems.
26
New methods to color the vertices of a graph
Daniel Brélaz · Communications of the ACM · 1979 · 1.6K citations · Full text
Learning Combinatorial Optimization Algorithms over Graphs
Hanjun Dai, Elias B. Khalil, Yuyu Zhang et al. · arXiv (Cornell University) · 2017 · 977 citations · Full text