Transferability of graph neural networks: an extended graphon approach

DOI10.1016/j.acha.2022.11.008OpenAlexW3201646649MaRDI QIDQ2677834

Gitta Kutyniok, Ron Levie, Sohir Maskey

Publication date: 6 January 2023

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

Full work available at URL: https://arxiv.org/abs/2109.10096

zbMATH Keywords

graphonstabilitygeneralizationspectral methodstransferabilitygraph neural network

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Graph theory (including graph drawing) in computer science (68R10) Functional calculus for linear operators (47A60)

Uses Software

• CayleyNets

Cites Work

• Unnamed Item
• Unnamed Item
• Operator-Lipschitz functions in Schatten-von Neumann classes
• Convergent sequences of dense graphs. II. Multiway cuts and statistical physics
• Limits of dense graph sequences
• Convergent sequences of dense graphs. I: Subgraph frequencies, metric properties and testing
• Operator Hölder-Zygmund functions
• Optimal graphon estimation in cut distance
• Numerical treatment of partial differential equations. Revised translation of the 3rd German edition of `Numerische Behandlung partieller Differentialgleichungen' by Martin Stynes.
• Operator Lipschitz functions
• CayleyNets: Graph Convolutional Neural Networks With Complex Rational Spectral Filters
• Stability Properties of Graph Neural Networks
• Graphon Filters: Graph Signal Processing in the Limit
• Graph Representation Learning
• Graphons, cut norm and distance, couplings and rearrangements
• Graphon Signal Processing
• Functional analysis