Permutation-invariant representations with applications to graph deep learning

DOI10.1016/J.ACHA.2025.101798MaRDI QIDQ6932279zbMATH OpenFDO

Authors Radu Balan, Naveed Haghani, Maneesh K. Singh

Publication date 9 September 2025

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

Full work available at URL https://doi.org/10.1016/J.ACHA.2025.101798

zbMATH Keywords

bi-Lipschitz embeddingframespermutation invariance

Mathematics Subject Classification ID

General harmonic expansions, frames (42C15) Graph theory (including graph drawing) in computer science (68R10) Metric embeddings as related to computational problems and algorithms (68R12) Artificial neural networks and deep learning (68T07)

Cites work

• Comparison between \(W_2\) distance and \(\dot{H}^{-1}\) norm, and localization of Wasserstein distance
• Complete set of translation invariant measurements with Lipschitz bounds
• Computational invariant theory
• Convex Sets and Nearest Points
• Finding a Global Optimal Solution for a Quadratically Constrained Fractional Quadratic Problem with Applications to the Regularized Total Least Squares
• Frames and phaseless reconstruction
• Full spark frames
• Full spark frames in the orbit of a representation
• scientific article; zbMATH DE number 3507416 (Why is no real title available?)
• scientific article; zbMATH DE number 1821400 (Why is no real title available?)
• scientific article; zbMATH DE number 1909499 (Why is no real title available?)
• Invertibility and robustness of phaseless reconstruction
• Linear optimal transport embedding: provable Wasserstein classification for certain rigid transformations and perturbations
• Low-dimensional invariant embeddings for universal geometric learning
• On Lipschitz analysis and Lipschitz synthesis for the phase retrieval problem
• On minimizing quadratically constrained ratio of two quadratic functions
• Real analysis
• Saving phase: injectivity and stability for phase retrieval
• Separating invariants and finite reflection groups
• Singularities and groups in bifurcation theory. Volume II
• Stable phase retrieval with low-redundancy frames
• Stable super-resolution limit and smallest singular value of restricted Fourier matrices
• Universal approximations of invariant maps by neural networks

Cited in

(2)

• The reflection-invariant bispectrum: signal recovery in the dihedral model
• Coarse embeddings of quotients by finite group actions

This page was built for publication: Permutation-invariant representations with applications to graph deep learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6932279)