Graph Neural Networks for Maximum Constraint Satisfaction

Abstract

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.

References in corpus (8)

• Growing Scale-Free Networks with Tunable Clustering
• Learning Combinatorial Optimization Algorithms over Graphs
• Combinatorial Optimization with Graph Convolutional Networks and Guided Tree Search
• Neural Combinatorial Optimization with Reinforcement Learning
• Extremal Optimization for Graph Partitioning
• Extremal Cuts of Sparse Random Graphs
• Coloring Big Graphs with AlphaGoZero
• Many Hard Examples in Exact Phase Transitions with Application to Generating Hard Satisfiable Instances

Cited by in corpus (1)

• Erdos Goes Neural: an Unsupervised Learning Framework for Combinatorial Optimization on Graphs