Vincent Gripon's Homepage

Research and Teaching Blog

A Unified Deep Learning Formalism For Processing Graph Signals

M. Bontonou, C. Lassance, J. Vialatte and V. Gripon, "A Unified Deep Learning Formalism For Processing Graph Signals," in SDM Special Session on Graph Neural Networks, May 2019.

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.

Download manuscript.

Bibtex
@inproceedings{BonLasViaGri20195,
  author = {Myriam Bontonou and Carlos Lassance and
Jean-Charles Vialatte and Vincent Gripon},
  title = {A Unified Deep Learning Formalism For
Processing Graph Signals},
  booktitle = {SDM Special Session on Graph Neural
Networks},
  year = {2019},
  month = {May},
}




You are the 831451th visitor

Vincent Gripon's Homepage