Graph convolutional neural networks via scattering

Journal Article (Journal Article)

We generalize the scattering transform to graphs and consequently construct a convolutional neural network on graphs. We show that under certain conditions, any feature generated by such a network is approximately invariant to permutations and stable to signal and graph manipulations. Numerical results demonstrate competitive performance on relevant datasets.

Full Text

Duke Authors

Cited Authors

  • Zou, D; Lerman, G

Published Date

  • November 1, 2020

Published In

Volume / Issue

  • 49 / 3

Start / End Page

  • 1046 - 1074

Electronic International Standard Serial Number (EISSN)

  • 1096-603X

International Standard Serial Number (ISSN)

  • 1063-5203

Digital Object Identifier (DOI)

  • 10.1016/j.acha.2019.06.003

Citation Source

  • Scopus