Geometric scattering on measure spaces
Applied and Computational Harmonic Analysis · 2024-05 · 70 · 101635
DOI: 10.1016/j.acha.2024.101635 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied and Computational Harmonic Analysis, 2024-05. Verfasst von Joyce Chew und 7 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 89 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIGMS NIH HHS, NICHD NIH HHS, National Science Foundation.
Abstract (Originalsprache)
The scattering transform is a multilayered, wavelet-based transform initially introduced as a mathematical model of convolutional neural networks (CNNs) that has played a foundational role in our understanding of these networks' stability and invariance properties. In subsequent years, there has been widespread interest in extending the success of CNNs to data sets with non-Euclidean structure, such as graphs and manifolds, leading to the emerging field of geometric deep learning. In order to improve our understanding of the architectures used in this new field, several papers have proposed generalizations of the scattering transform for non-Euclidean data structures such as undirected graphs and compact Riemannian manifolds without boundary. Analogous to the original scattering transform, these works prove that these variants of the scattering transform have desirable stability and invariance properties and aim to improve our understanding of the neural networks used in geometric deep learning. In this paper, we introduce a general, unified model for geometric scattering on measure spaces. Our proposed framework includes previous work on compact Riemannian manifolds without boundary and undirected graphs as special cases but also applies to more general settings such as directed graphs, signed graphs, and manifolds with boundary. We propose a new criterion that identifies to which groups a useful representation should be invariant and show that this criterion is sufficient to guarantee that the scattering transform has desirable stability and invariance properties. Additionally, we consider finite measure spaces that are obtained from randomly sampling an unknown manifold. We propose two methods for constructing a data-driven graph on which the associated graph scattering transform approximates the scattering transform on the underlying manifold. Moreover, we use a diffusion-maps based approach to prove quantitative estimates on the rate of convergence of one of these approximations as the number of sample points tends to infinity. Lastly, we showcase the utility of our method on spherical images, a directed graph stochastic block model, and on high-dimensional single-cell data.
Förderung
- NIGMS NIH HHS
- NICHD NIH HHS
- National Science Foundation
- National Institutes of Health
Zitieren
APA
Chew, J., Hirn, M., Krishnaswamy, S., Needell, D., Perlmutter, M., Steach, H., Viswanath, S., & Wu, H. T. (2024). Geometric scattering on measure spaces. Applied and Computational Harmonic Analysis, 70, 101635. https://doi.org/10.1016/j.acha.2024.101635
Vancouver
Chew J, Hirn M, Krishnaswamy S, Needell D, Perlmutter M, Steach H, et al. Geometric scattering on measure spaces. Applied and Computational Harmonic Analysis. 2024;70:101635. doi:10.1016/j.acha.2024.101635
BibTeX
@article{Chew2024,
author = {Chew, Joyce and Hirn, Matthew and Krishnaswamy, Smita and Needell, Deanna and Perlmutter, Michael and Steach, Holly and Viswanath, Siddharth and Wu, Hau-Tieng},
title = {Geometric scattering on measure spaces},
journal = {Applied and Computational Harmonic Analysis},
year = {2024},
volume = {70},
pages = {101635},
doi = {10.1016/j.acha.2024.101635}
}
EUVIMED