Transferability of graph neural networks: An extended graphon approach

We study spectral graph convolutional neural networks (GCNNs), where filters are defined as continuous functions of the graph shift operator (GSO) through functional calculus. A spectral GCNN is not tailored to one specific graph and can be transferred between different graphs. It is hence important...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Applied and computational harmonic analysis Jg. 63; S. 48 - 83
Hauptverfasser:	Maskey, Sohir, Levie, Ron, Kutyniok, Gitta
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Elsevier Inc 01.03.2023
Schlagworte:	Generalization Graph neural network Graphon Spectral methods Stability Transferability Graphon Stability Graph neural network 68T07 Transferability 68R10 Generalization 47A60 Spectral methods
ISSN:	1063-5203, 1096-603X
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!