Aarhus University Seal

Horizontal Flows and Manifold Stochastics in Geometric Deep Learning

by Stefan Sommer and Alex Bronstein
CSGB Research Reports Number 2 (February 2020)

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.

Keywords: geometric deep learning, stochastic analysis on manifolds, geometric statistics, frame bundle, curvature, bridge sampling.

Format available: PDF (1 MB)