D-DARTS: Distributed Differentiable Architecture Search - Informatique, Biologie Intégrative et Systèmes Complexes Accéder directement au contenu
Article Dans Une Revue Pattern Recognition Letters Année : 2023

D-DARTS: Distributed Differentiable Architecture Search

Résumé

Differentiable ARchiTecture Search (DARTS) is one of the most trending Neural Architecture Search (NAS) methods. It drastically reduces search cost by resorting to weight-sharing. However, this approach also dramatically reduces the search space, thus excluding potential promising architectures. In this article, we propose D-DARTS, a solution that addresses this problem by nesting neural networks at the cell level instead of using weight-sharing to produce more diversified and specialized architectures. Moreover, we introduce a novel algorithm that can derive deeper architectures from a few trained cells, increasing performance and saving computation time. In addition, we introduce DARTOpti, an alternative search space in which we optimize existing handcrafted architectures instead of searching from scratch. Our solution reaches competitive performance on image classification tasks.
Fichier principal
Vignette du fichier
D_DARTS_PRL (1).pdf (850.27 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
licence

Dates et versions

hal-04270973 , version 1 (02-06-2024)

Licence

Identifiants

Citer

Alexandre Heuillet, Hedi Tabia, Hichem Arioui, Kamal Youcef-Toumi. D-DARTS: Distributed Differentiable Architecture Search. Pattern Recognition Letters, 2023, 176, pp.42--48. ⟨10.1016/j.patrec.2023.10.019⟩. ⟨hal-04270973⟩
48 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More