Un modèle unifié pour la classification de signaux sur graphe avec de l’apprentissage profond
We propose to review some of the major models performing supervised classification of graph signals in deep learning. The goal of supervised classification of graph signals is to classify a signal whose components are defined on the vertices of a graph. Convolutional Neural Networks (CNN) are very efficient at classifying signals defined on a grid graph (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 to any graph. The overall purpose of this study is to provide a comparison of some of the major models in supervised classification of graph signals. We also introduce a unified formalism.
Télécharger le manuscrit.
Bibtex@inproceedings{BonLasViaGri201908,
author = {Myriam Bontonou and Carlos Lassance and
Jean-Charles Vialatte and Vincent Gripon},
title = {Un modèle unifié pour la classification
de signaux sur graphe avec de l’apprentissage
profond},
booktitle = {GRETSI},
year = {2019},
month = {August},
}