Generating graph perturbations to enhance the generalization of GNNs

Graph neural networks (GNNs) have become the standard approach for performing machine learning on graphs. Such models need large amounts of training data, however, in several graph classification and regression tasks, only limited training data is available. Unfortunately, due to the complex nature...

Szczegółowa specyfikacja

Opis bibliograficzny

Główni autorzy:	Sofiane Ennadir, Giannis Nikolentzos, Michalis Vazirgiannis, Henrik Boström
Format:	Artigo
Język:	Inglês
Wydane:	KeAi Communications Co. Ltd. 2024-01-01
Seria:	AI Open
Hasła przedmiotowe:	Generalization Graph neural networks Data augmentation
Dostęp online:	http://www.sciencedirect.com/science/article/pii/S2666651024000184
Etykiety:	Dodaj etykietę Nie ma etykietki, Dołącz pierwszą etykiete!