Understanding Graph Neural Networks with Generalized Geometric Scattering Transforms
From MaRDI portal
Graph representations (geometric and intersection representations, etc.) (05C62) Random walks on graphs (05C81) General harmonic expansions, frames (42C15) Nontrigonometric harmonic analysis involving wavelets and other special systems (42C40) Graph theory (including graph drawing) in computer science (68R10) Artificial neural networks and deep learning (68T07)
Abstract: The scattering transform is a multilayered wavelet-based deep learning architecture that acts as a model of convolutional neural networks. Recently, several works have introduced generalizations of the scattering transform for non-Euclidean settings such as graphs. Our work builds upon these constructions by introducing windowed and non-windowed geometric scattering transforms for graphs based upon a very general class of asymmetric wavelets. We show that these asymmetric graph scattering transforms have many of the same theoretical guarantees as their symmetric counterparts. As a result, the proposed construction unifies and extends known theoretical results for many of the existing graph scattering architectures. In doing so, this work helps bridge the gap between geometric scattering and other graph neural networks by introducing a large family of networks with provable stability and invariance guarantees. These results lay the groundwork for future deep learning architectures for graph-structured data that have learned filters and also provably have desirable theoretical properties.
Cites work
- A graph discretization of the Laplace-Beltrami operator
- CayleyNets: Graph Convolutional Neural Networks With Complex Rational Spectral Filters
- Deep Haar scattering networks
- Diffusion maps
- Diffusion maps, spectral clustering and reaction coordinates of dynamical systems
- Eigenvalues of Laplacians on a Closed Riemannian Manifold and Its Nets
- Error estimates for spectral convergence of the graph Laplacian on random geometric graphs toward the Laplace-Beltrami operator
- From graph to manifold Laplacian: the convergence rate
- Graph convolutional neural networks via scattering
- Group invariant scattering
- Transferability of spectral graph convolutional neural networks
- Wavelet Scattering Regression of Quantum Chemical Energies
Cited in
(2)
This page was built for publication: Understanding Graph Neural Networks with Generalized Geometric Scattering Transforms
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6070299)
