Graph Convolutional Neural Networks via Scattering
This work addresses the challenge of developing stable and invariant graph neural networks for graph-based data analysis, representing an incremental advancement by adapting an existing transform to a new domain.
The authors tackled the problem of constructing convolutional neural networks on graphs by generalizing the scattering transform, achieving approximate invariance to permutations and stability to graph manipulations under certain conditions, with numerical results showing competitive performance on relevant datasets.
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.