Graph Convolutional Neural Networks via Scattering

Dongmian Zou; Gilad Lerman

doi:10.1016/j.acha.2019.06.003

Graph Convolutional Neural Networks via Scattering

Information Theory 2020-09-10 v2 Machine Learning Signal Processing math.IT

Authors: Dongmian Zou , Gilad Lerman

View on arXiv ↗ PDF ↗ DOI ↗

Abstract

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 graph manipulations. Numerical results demonstrate competitive performance on relevant datasets.

Keywords

graph generation graph convolutional network graph neural network

Cite

@article{arxiv.1804.00099,
  title  = {Graph Convolutional Neural Networks via Scattering},
  author = {Dongmian Zou and Gilad Lerman},
  journal= {arXiv preprint arXiv:1804.00099},
  year   = {2020}
}

Comments

26 pages, 9 figures, 4 tables

Related papers

View all related →