GRASP-GCN: Graph-Shape Prioritization for Neural Architecture Search under Distribution Shifts

Neural Architecture Search (NAS) methods have shown to output networks that largely outperform human-designed networks. However, conventional NAS methods have mostly tackled the single dataset scenario, incuring in a large computational cost as the procedure has to be run from scratch for every new...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2024-05
Hauptverfasser:	Casarin, Sofia, Lanz, Oswald, Escalera, Sergio
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Artificial neural networks Computational efficiency Datasets Searching
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!