Graph Neural Networks for Maximum Constraint Satisfaction

September 18, 2019 Β· Declared Dead Β· πŸ› Frontiers in Artificial Intelligence

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Jan Toenshoff, Martin Ritzert, Hinrikus Wolf, Martin Grohe arXiv ID 1909.08387 Category cs.AI: Artificial Intelligence Cross-listed cs.LG Citations 67 Venue Frontiers in Artificial Intelligence Last Checked 3 months ago
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.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Artificial Intelligence

Died the same way β€” πŸ‘» Ghosted