CNN architectures for GRAPH data

Conference Paper (2019)
Author(s)

Fernando Gama (University of Pennsylvania)

Antonio G. Marques (King Juan Carlos University)

G. Leus (TU Delft - Signal Processing Systems)

Alejandro Ribeiro (University of Pennsylvania)

Research Group
Signal Processing Systems
Copyright
© 2019 F. Gama, Antonio G. Marques, G.J.T. Leus, Alejandro Ribeiro
DOI related publication
https://doi.org/10.1109/GlobalSIP.2018.8646348
More Info
expand_more
Publication Year
2019
Language
English
Copyright
© 2019 F. Gama, Antonio G. Marques, G.J.T. Leus, Alejandro Ribeiro
Research Group
Signal Processing Systems
Pages (from-to)
723-724
ISBN (print)
978-1-7281-1296-1
ISBN (electronic)
978-1-7281-1295-4
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

In this ongoing work, we describe several architectures that generalize convolutional neural networks (CNNs) to process signals supported on graphs. The general idea of the replace time invariant filters with graph filters to generate convolutional features and to replace pooling with sampling schemes for graph signals. The different architectures are compared and the key trade offs are identified. Numerical simulations with both synthetic and real-world data are used to illustrate the advantages of the proposed approaches.

Files

CNN_ARCHITECTURES_FOR_GRAPH_DA... (pdf)
(pdf | 0.203 Mb)
- Embargo expired in 21-08-2019
License info not available