Graph Convolutional Neural Networks via Scattering
arXiv:1804.00099 · doi:10.1016/j.acha.2019.06.003
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.
26 pages, 9 figures, 4 tables