Graph convolutional neural networks via scattering

DOI10.1016/j.acha.2019.06.003zbMath1447.62111arXiv1804.00099OpenAlexW3104104151MaRDI QIDQ2197959

Gilad Lerman, Dongmian Zou

Publication date: 1 September 2020

Published in: Applied and Computational Harmonic Analysis (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1804.00099

zbMATH Keywords

waveletsscattering transformspectral graph theorypermutation invariancefeature learninggraph convolutiongraph neural networks

Mathematics Subject Classification ID

Nontrigonometric harmonic analysis involving wavelets and other special systems (42C40) Knowledge representation (68T30) Neural nets and related approaches to inference from stochastic processes (62M45) Probabilistic graphical models (62H22)

Related Items

Understanding Graph Neural Networks with Generalized Geometric Scattering Transforms ⋮ Central and Noncentral Limit Theorems Arising from the Scattering Transform and Its Neural Activation Generalization ⋮ Geometric scattering on measure spaces ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Rotationally invariant time-frequency scattering transforms

Cites Work

• Unnamed Item
• Unnamed Item
• Wavelets on graphs via spectral graph theory
• Vertex-frequency analysis on graphs
• Diffusion wavelets
• Group Invariant Scattering
• Ten Lectures on Wavelets
• Community Detection and Stochastic Block Models
• Discrete Signal Processing on Graphs: Frequency Analysis
• Energy Propagation in Deep Convolutional Neural Networks
• A useful variant of the Davis–Kahan theorem for statisticians
• The Rotation of Eigenvectors by a Perturbation. III