Hyperbolic Neural Networks

05/23/2018
by   Octavian-Eugen Ganea, et al.
0

Hyperbolic spaces have recently gained momentum in the context of machine learning due to their high capacity and tree-likeliness properties. However, the representational power of hyperbolic geometry is not yet on par with Euclidean geometry, mostly because of the absence of corresponding hyperbolic neural network layers. This makes it hard to use hyperbolic embeddings in downstream tasks. Here, we bridge this gap in a principled manner by combining the formalism of Möbius gyrovector spaces with the Riemannian geometry of the Poincaré model of hyperbolic spaces. As a result, we derive hyperbolic versions of important deep learning tools: multinomial logistic regression, feed-forward and recurrent neural networks such as gated recurrent units. This allows to embed sequential data and perform classification in the hyperbolic space. Empirically, we show that, even if hyperbolic optimization tools are limited, hyperbolic sentence embeddings either outperform or are on par with their Euclidean variants on textual entailment and noisy-prefix recognition tasks.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/03/2018

Hyperbolic Entailment Cones for Learning Hierarchical Embeddings

Learning graph representations via low-dimensional embeddings that prese...
research
05/24/2018

Hyperbolic Attention Networks

We introduce hyperbolic attention networks to endow neural networks with...
research
02/10/2021

Hyperbolic Generative Adversarial Network

Recently, Hyperbolic Spaces in the context of Non-Euclidean Deep Learnin...
research
06/15/2023

Hyperbolic Convolution via Kernel Point Aggregation

Learning representations according to the underlying geometry is of vita...
research
03/14/2022

FisheyeHDK: Hyperbolic Deformable Kernel Learning for Ultra-Wide Field-of-View Image Recognition

Conventional convolution neural networks (CNNs) trained on narrow Field-...
research
11/14/2019

The Isoperimetric Problem in a Lattice of H^3

The isoperimetric problem is one of the oldest in geometry and it consis...
research
02/28/2022

Hyperbolic Graph Neural Networks: A Review of Methods and Applications

Graph neural networks generalize conventional neural networks to graph-s...

Please sign up or login with your details

Forgot password? Click here to reset