When Spectral Domain Meets Spatial Domain in Graph Neural Networks - Normandie Université Accéder directement au contenu
Communication Dans Un Congrès Année : 2020

When Spectral Domain Meets Spatial Domain in Graph Neural Networks

Résumé

Convolutional Graph Neural Networks (Con-vGNNs) are designed either in the spectral domain or in the spatial domain. In this paper, we provide a theoretical framework to analyze these neural networks, by deriving some equivalence of the graph convolution processes, regardless if they are designed in the spatial or the spectral domain. We demonstrate the relevance of the proposed framework by providing a spectral analysis of the most popular ConvGNNs (ChebNet, CayleyNet, GCN and Graph Attention Networks), which allows to explain their performance and shows their limits.
Fichier principal
Vignette du fichier
20.icml.gnn.pdf (933.37 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03088374 , version 1 (26-12-2020)

Identifiants

  • HAL Id : hal-03088374 , version 1

Citer

Balcilar Muhammet, Renton Guillaume, Héroux Pierre, Gaüzère Benoit, Adam Sébastien, et al.. When Spectral Domain Meets Spatial Domain in Graph Neural Networks. Thirty-seventh International Conference on Machine Learning (ICML 2020) - Workshop on Graph Representation Learning and Beyond (GRL+ 2020), Jul 2020, Vienna, Austria. ⟨hal-03088374⟩
280 Consultations
181 Téléchargements

Partager

Gmail Facebook X LinkedIn More