CNN architectures for GRAPH data
Fernando Gama (University of Pennsylvania)
Antonio G. Marques (King Juan Carlos University)
G. Leus (TU Delft - Signal Processing Systems)
Alejandro Ribeiro (University of Pennsylvania)
More Info
expand_more
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.