Horizontal Flows and Manifold Stochastics in Geometric Deep Learning

Stefan Sommer, Alex M. Bronstein

Research output: Contribution to journalJournal articleResearchpeer-review

7 Citations (Scopus)
36 Downloads (Pure)

Abstract

We introduce two constructions in geometric deep learning for 1) transporting orientation-dependent convolutional filters over a manifold in a continuous way and thereby defining a convolution operator that naturally incorporates the rotational effect of holonomy; and 2) allowing efficient evaluation of manifold convolution layers by sampling manifold valued random variables that center around a weighted diffusion mean. Both methods are inspired by stochastics on manifolds and geometric statistics, and provide examples of how stochastic methods – here horizontal frame bundle flows and non-linear bridge sampling schemes, can be used in geometric deep learning. We outline the theoretical foundation of the two methods, discuss their relation to Euclidean deep networks and existing methodology in geometric deep learning, and establish important properties of the proposed constructions.
Original languageEnglish
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
Volume44
Issue number2
Pages (from-to)811 - 822
ISSN0162-8828
DOIs
Publication statusPublished - 2021

Cite this