A Differentiable Gaussian-like Distribution on Hyperbolic Space for Gradient-Based Learning

by   Yoshihiro Nagano, et al.

Hyperbolic space is a geometry that is known to be well-suited for representation learning of data with an underlying hierarchical structure. In this paper, we present a novel hyperbolic distribution called pseudo-hyperbolic Gaussian, a Gaussian-like distribution on hyperbolic space whose density can be evaluated analytically and differentiated with respect to the parameters. Our distribution enables the gradient-based learning of the probabilistic models on hyperbolic space that could never have been considered before. Also, we can sample from this hyperbolic probability distribution without resorting to auxiliary means like rejection sampling. As applications of our distribution, we develop a hyperbolic-analog of variational autoencoder and a method of probabilistic word embedding on hyperbolic space. We demonstrate the efficacy of our distribution on various datasets including MNIST, Atari 2600 Breakout, and WordNet.


page 5

page 7

page 8

page 13

page 15

page 16


Hyperbolic Variational Graph Neural Network for Modeling Dynamic Graphs

Learning representations for graphs plays a critical role in a wide spec...

A Rotated Hyperbolic Wrapped Normal Distribution for Hierarchical Representation Learning

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

Hyperbolic Graph Diffusion Model for Molecule Generation

Recently, diffusion models have achieved remarkable performance in data ...

Hyperbolic Diffusion Embedding and Distance for Hierarchical Representation Learning

Finding meaningful representations and distances of hierarchical data is...

Learning Hyperbolic Representations for Unsupervised 3D Segmentation

There exists a need for unsupervised 3D segmentation on complex volumetr...

Estimation of spatially varying parameters with application to hyperbolic SPDEs

More often than not, we encounter problems with varying parameters as op...

Code Repositories



view repo

Please sign up or login with your details

Forgot password? Click here to reset