DeepAI AI Chat
Log In Sign Up

Ultrahyperbolic Representation Learning

by   Marc T. Law, et al.

In machine learning, data is usually represented in a (flat) Euclidean space where distances between points are along straight lines. Researchers have recently considered more exotic (non-Euclidean) Riemannian manifolds such as hyperbolic space which is well suited for tree-like data. In this paper, we propose a representation living on a pseudo-Riemannian manifold with constant nonzero curvature. It is a generalization of hyperbolic and spherical geometries where the nondegenerate metric tensor is not positive definite. We provide the necessary learning tools in this geometry and extend gradient method optimization techniques. More specifically, we provide closed-form expressions for distances via geodesics and define a descent direction that guarantees the minimization of the objective problem. Our novel framework is applied to graph representations.


Geodesic Exponential Kernels: When Curvature and Linearity Conflict

We consider kernel methods on general geodesic metric spaces and provide...

Differentiating through the Fréchet Mean

Recent advances in deep representation learning on Riemannian manifolds ...

Representation of 2D frame less visual space as a neural manifold and its information geometric interpretation

Representation of 2D frame less visual space as neural manifold and its ...

Linear Classifiers in Mixed Constant Curvature Spaces

Embedding methods for mixed-curvature spaces are powerful techniques for...

Learning phylogenetic trees as hyperbolic point configurations

An alternative to independent pairwise distance estimation is proposed t...

Learning Graph Embeddings on Constant-Curvature Manifolds for Change Detection in Graph Streams

The space of graphs is characterized by a non-trivial geometry, which of...

Geometric Mean Metric Learning

We revisit the task of learning a Euclidean metric from data. We approac...

Code Repositories


Ultrahyperbolic Representation Learning

view repo