Geometric Wavelet Scattering Networks on Compact Riemannian Manifolds

Michael Perlmutter, Feng Gao, Guy Wolf, Matthew Hirn

Research output: Contribution to journalConference articlepeer-review

12 Scopus citations

Abstract

The Euclidean scattering transform was introduced nearly a decade ago to improve the mathematical understanding of convolutional neural networks. Inspired by recent interest in geometric deep learning, which aims to generalize convolutional neural networks to manifold and graph-structured domains, we define a geometric scattering transform on manifolds. Similar to the Euclidean scattering transform, the geometric scattering transform is based on a cascade of wavelet filters and pointwise nonlinearities. It is invariant to local isometries and stable to certain types of diffeomorphisms. Empirical results demonstrate its utility on several geometric learning tasks. Our results generalize the deformation stability and local translation invariance of Euclidean scattering, and demonstrate the importance of linking the used filter structures to the underlying geometry of the data.

Original languageEnglish
Pages (from-to)570-604
Number of pages35
JournalProceedings of Machine Learning Research
Volume107
StatePublished - 2020
Event1st Mathematical and Scientific Machine Learning Conference, MSML 2020 - Princeton, United States
Duration: 20 Jul 202024 Jul 2020

Keywords

  • geometric deep learning
  • spectral geometry
  • wavelet scattering

Fingerprint

Dive into the research topics of 'Geometric Wavelet Scattering Networks on Compact Riemannian Manifolds'. Together they form a unique fingerprint.

Cite this