CNN architectures for GRAPH data

CNN architectures for GRAPH data

Gama, F. (University of Pennsylvania)
Marques, Antonio G. (King Juan Carlos University)
Leus, G.J.T. (TU Delft Signal Processing Systems)
Ribeiro, Alejandro (University of Pennsylvania)

2019

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.

Convolutional neural networks
Deep learning
Geometric learning
Graph signal processing

http://resolver.tudelft.nl/uuid:add3cb34-1a6d-4271-8502-e879608878ad

https://doi.org/10.1109/GlobalSIP.2018.8646348

IEEE, Piscataway

2019-08-21

978-1-7281-1296-1

2018 IEEE Global Conference on Signal and Information Processing (GlobalSIP): Proceedings

2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018, 2018-11-26 → 2018-11-29, Anaheim, United States

Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

Institutional Repository

conference paper

© 2019 F. Gama, Antonio G. Marques, G.J.T. Leus, Alejandro Ribeiro