Graph convolutional neural networks via scattering

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 resu...

Full description

Saved in:
Bibliographic Details
Published in:Applied and computational harmonic analysis 2020-11, Vol.49 (3), p.1046-1074
Main Authors: Zou, Dongmian, Lerman, Gilad
Format: Article
Language:English
Subjects:
Feature learning
Graph convolution
Graph neural networks
Permutation invariance
Scattering transform
Spectral graph theory
Wavelets
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:1063-5203
1096-603X
DOI:10.1016/j.acha.2019.06.003