Bridging the Gap Between Spectral and Spatial Domains in Graph Neural Networks

This paper aims at revisiting Graph Convolutional Neural Networks by bridging the gap between spectral and spatial design of graph convolutions. We theoretically demonstrate some equivalence of the graph convolution process regardless it is designed in the spatial or the spectral domain. The obtaine...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2020-03
Hauptverfasser:	Balcilar, Muhammet, Renton, Guillaume, Heroux, Pierre, Gauzere, Benoit, Adam, Sebastien, Honeine, Paul
Format:	Artikel
Sprache:	eng
Schlagworte:	Artificial neural networks Convolution Design Domains Graph neural networks Neural networks Spectra Spectrum analysis
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!