Skip to main content
Journal cover image

Graph convolutional neural networks via scattering

Publication ,  Journal Article
Zou, D; Lerman, G
Published in: Applied and Computational Harmonic Analysis
November 1, 2020

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.

Duke Scholars

Altmetric Attention Stats
Dimensions Citation Stats

Published In

Applied and Computational Harmonic Analysis

DOI

EISSN

1096-603X

ISSN

1063-5203

Publication Date

November 1, 2020

Volume

49

Issue

3

Start / End Page

1046 / 1074

Related Subject Headings

  • Numerical & Computational Mathematics
  • 4904 Pure mathematics
  • 4901 Applied mathematics
  • 0103 Numerical and Computational Mathematics
  • 0102 Applied Mathematics
  • 0101 Pure Mathematics
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Zou, D., & Lerman, G. (2020). Graph convolutional neural networks via scattering. Applied and Computational Harmonic Analysis, 49(3), 1046–1074. https://doi.org/10.1016/j.acha.2019.06.003
Zou, D., and G. Lerman. “Graph convolutional neural networks via scattering.” Applied and Computational Harmonic Analysis 49, no. 3 (November 1, 2020): 1046–74. https://doi.org/10.1016/j.acha.2019.06.003.
Zou D, Lerman G. Graph convolutional neural networks via scattering. Applied and Computational Harmonic Analysis. 2020 Nov 1;49(3):1046–74.
Zou, D., and G. Lerman. “Graph convolutional neural networks via scattering.” Applied and Computational Harmonic Analysis, vol. 49, no. 3, Nov. 2020, pp. 1046–74. Scopus, doi:10.1016/j.acha.2019.06.003.
Zou D, Lerman G. Graph convolutional neural networks via scattering. Applied and Computational Harmonic Analysis. 2020 Nov 1;49(3):1046–1074.
Journal cover image

Published In

Applied and Computational Harmonic Analysis

DOI

EISSN

1096-603X

ISSN

1063-5203

Publication Date

November 1, 2020

Volume

49

Issue

3

Start / End Page

1046 / 1074

Related Subject Headings

  • Numerical & Computational Mathematics
  • 4904 Pure mathematics
  • 4901 Applied mathematics
  • 0103 Numerical and Computational Mathematics
  • 0102 Applied Mathematics
  • 0101 Pure Mathematics