A Unified Deep Learning Formalism For Processing Graph Signals - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2020

A Unified Deep Learning Formalism For Processing Graph Signals

Myriam Bontonou
Jean-Charles Vialatte
  • Fonction : Auteur
  • PersonId : 1006644

Résumé

Convolutional Neural Networks are very efficient at processing signals defined on a discrete Euclidean space (such as images). However, as they can not be used on signals defined on an arbitrary graph, other models have emerged, aiming to extend its properties. We propose to review some of the major deep learning models designed to exploit the underlying graph structure of signals. We express them in a unified formalism, giving them a new and comparative reading.

Dates et versions

hal-02487422 , version 1 (21-02-2020)

Identifiants

Citer

Myriam Bontonou, Carlos Lassance, Jean-Charles Vialatte, Vincent Gripon. A Unified Deep Learning Formalism For Processing Graph Signals. 2020. ⟨hal-02487422⟩
22 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More