“Geometric Deep Learning: Going beyond Euclidean data” (2017), by Michael M. Bronstein et al. Computer Science research paper. Original abstract below, unchanged. A free PDF is available.

Geometric Deep Learning: Going beyond Euclidean data

Michael M. Bronstein, Joan Bruna, Yann LeCun et al. · July 1, 2017 · Computer Science

Abstract

Geometric deep learning is an umbrella term for emerging techniques attempting to generalize (structured) deep neural models to non-Euclidean domains, such as graphs and manifolds. The purpose of this article is to overview different examples of geometric deep-learning problems and present available solutions, key difficulties, applications, and future research directions in this nascent field.

Free PDF DOI: 10.1109/msp.2017.2693418