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 FAST JOINT CARE + train on relatively small instances; the resulting networks Default 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.