← Search

Martin Keller-Ressel

2 accepted papers

2021

Hyperbolic Busemann Learning with Ideal Prototypes

NeurIPS 2021poster

Hyperbolic space has become a popular choice of manifold for representation learning of various datatypes from tree-like structures and text to graphs. Building on the success of deep learning with prototypes in Euclidean and hyperspherical spaces, a few recent works have proposed hyperbolic prototy…