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.
Original language | English |
---|---|
Title of host publication | 2018 IEEE Global Conference on Signal and Information Processing (GlobalSIP) |
Subtitle of host publication | Proceedings |
Place of Publication | Piscataway |
Publisher | IEEE |
Pages | 723-724 |
Number of pages | 2 |
ISBN (Electronic) | 978-1-7281-1295-4 |
ISBN (Print) | 978-1-7281-1296-1 |
DOIs | |
Publication status | Published - 2019 |
Event | 2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Anaheim, United States Duration: 26 Nov 2018 → 29 Nov 2018 |
Conference
Conference | 2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 |
---|---|
Country/Territory | United States |
City | Anaheim |
Period | 26/11/18 → 29/11/18 |
Bibliographical note
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-careOtherwise 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.
Keywords
- Convolutional neural networks
- Deep learning
- Geometric learning
- Graph signal processing