Are Graph Neural Networks Optimal Approximation Algorithms?
Morris Yau, Nikolaos Karalias, Eric Hanqing Lu, Jessica Xu, Stefanie Jegelka
Abstract
In this work we design graph neural network architectures that capture optimal approximation algorithms for a large class of combinatorial optimization problems, using powerful algorithmic tools from semidefinite programming (SDP). Concretely, we prove that polynomial-sized message-passing algorithms can represent the most powerful polynomial time algorithms for Max Constraint Satisfaction Problems assuming the Unique Games Conjecture. We leverage this result to construct efficient graph neural network architectures, OptGNN, that obtain high quality approximate solutions on landmark combinatorial optimization problems such as Max-Cut, Min-Vertex-Cover, and Max-3-SAT. Our approach achieves strong empirical results across a wide range of real-world and synthetic datasets against solvers and neural baselines. Finally, we take advantage of OptGNN’s ability to capture convex relaxations to design an algorithm for producing bounds on the optimal solution from the learned embeddings of OptGNN.
BibTeX
@inproceedings{
yau2024are,
title={Are Graph Neural Networks Optimal Approximation Algorithms?},
author={Morris Yau and Nikolaos Karalias and Eric Hanqing Lu and Jessica Xu and Stefanie Jegelka},
booktitle={The Thirty-eighth Annual Conference on Neural Information Processing Systems},
year={2024},
url={https://openreview.net/forum?id=SxRblm9aMs}
}