Graph Convolutional Neural Networks via Scattering

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.

arXiv comment26 pages, 9 figures, 4 tables

References in corpus (2)

• Community detection in graphs
• Geometric deep learning: going beyond Euclidean data

Cited by in corpus (10)

• Graph Neural Networks with convolutional ARMA filters
• Stability Properties of Graph Neural Networks
• Graphs, Convolutions, and Neural Networks: From Graph Filters to Graph Neural Networks
• Graph Neural Networks: Taxonomy, Advances and Trends
• Algebraic Neural Networks: Stability to Deformations
• Wide and Deep Graph Neural Network with Distributed Online Learning
• Geometric Scattering Attention Networks
• Geometric Scattering on Measure Spaces
• Energy Propagation in Scattering Convolution Networks Can Be Arbitrarily Slow
• A short review on the maximum clique problem algorithms with classical, AI, and quantum methods