Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Graph Neural Networks for Maximum Constraint Satisfaction

About

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.

Jan Toenshoff, Martin Ritzert, Hinrikus Wolf, Martin Grohe• 2019

Related benchmarks

TaskDatasetResultRank
Maximum CliqueTwitter MC instances (static)
Mean ApR0.917
38
Maximum CliqueRB200 MC instances (static)
Mean ApR78.6
38
Maximum CliqueRB500 MC instances (static)
Mean ApR79.3
36
MaxCutGset (test)
ApR1
33
Maximum CliqueCOLLAB MC instances static
Mean ApR0.969
6
Showing 5 of 5 rows

Other info

Follow for update