DeepAI AI Chat
Log In Sign Up

Hyperbolic Busemann Learning with Ideal Prototypes

by   Mina Ghadimi Atigh, et al.

Hyperbolic space has become a popular choice of manifold for representation learning of arbitrary data, 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 prototypes for classification. Such approaches enable effective learning in low-dimensional output spaces and can exploit hierarchical relations amongst classes, but require privileged information about class labels to position the hyperbolic prototypes. In this work, we propose Hyperbolic Busemann Learning. The main idea behind our approach is to position prototypes on the ideal boundary of the Poincare ball, which does not require prior label knowledge. To be able to compute proximities to ideal prototypes, we introduce the penalised Busemann loss. We provide theory supporting the use of ideal prototypes and the proposed loss by proving its equivalence to logistic regression in the one-dimensional case. Empirically, we show that our approach provides a natural interpretation of classification confidence, while outperforming recent hyperspherical and hyperbolic prototype approaches.


A Theory of Hyperbolic Prototype Learning

We introduce Hyperbolic Prototype Learning, a type of supervised learnin...

HMSN: Hyperbolic Self-Supervised Learning by Clustering with Ideal Prototypes

Hyperbolic manifolds for visual representation learning allow for effect...

The Isoperimetric Problem in a Lattice of H^3

The isoperimetric problem is one of the oldest in geometry and it consis...

Shadow Cones: Unveiling Partial Orders in Hyperbolic Space

Hyperbolic space has been shown to produce superior low-dimensional embe...

A Rotated Hyperbolic Wrapped Normal Distribution for Hierarchical Representation Learning

We present a rotated hyperbolic wrapped normal distribution (RoWN), a si...

Hyperbolic Manifold Regression

Geometric representation learning has recently shown great promise in se...

Hyperbolic Random Forests

Hyperbolic space is becoming a popular choice for representing data due ...