Horizontal Flows and Manifold Stochastics in Geometric Deep Learning

Stefan Sommer, Alex M. Bronstein

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

7 Citationer (Scopus)
35 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 Brownian motion maximum likelihood 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.
OriginalsprogEngelsk
TidsskriftIEEE Transactions on Pattern Analysis and Machine Intelligence
Vol/bind44
Udgave nummer2
Sider (fra-til)811 - 822
ISSN0162-8828
DOI
StatusUdgivet - 2021

Citationsformater