The Deep Equilibrium Algorithmic Reasoner
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910403051651072 |
|---|---|
| author | Georgiev, Dobrik Liò, Pietro Buffelli, Davide |
| author_facet | Georgiev, Dobrik Liò, Pietro Buffelli, Davide |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_06445 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | The Deep Equilibrium Algorithmic Reasoner Georgiev, Dobrik Liò, Pietro Buffelli, Davide Machine Learning 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. |
| title | The Deep Equilibrium Algorithmic Reasoner |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2402.06445 |