Recent work on neural algorithmic reasoning has demonstrated that graph neural networks (GNNs) could learn to execute classical algorithms. Doing so, however, has always used a recurrent architecture, where each iteration of the GNN aligns with an algorithm's iteration. Since an algorithm's solution is often an equilibrium, we conjecture and empirically validate that one can train a network to solve algorithmic problems by directly finding the equilibrium. Note that this does not require matching each GNN iteration with a step of the algorithm.
@article{arxiv.2402.06445,
title = {The Deep Equilibrium Algorithmic Reasoner},
author = {Dobrik Georgiev and Pietro Liò and Davide Buffelli},
journal= {arXiv preprint arXiv:2402.06445},
year = {2024}
}