English

The Deep Equilibrium Algorithmic Reasoner

Machine Learning 2024-04-10 v2

Abstract

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.

Keywords

Cite

@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}
}
R2 v1 2026-06-28T14:44:06.868Z