DeepAI AI Chat
Log In Sign Up

Low-rank approximations of hyperbolic embeddings

by   Pratik Jawanpuria, et al.

The hyperbolic manifold is a smooth manifold of negative constant curvature. While the hyperbolic manifold is well-studied in the literature, it has gained interest in the machine learning and natural language processing communities lately due to its usefulness in modeling continuous hierarchies. Tasks with hierarchical structures are ubiquitous in those fields and there is a general interest to learning hyperbolic representations or embeddings of such tasks. Additionally, these embeddings of related tasks may also share a low-rank subspace. In this work, we propose to learn hyperbolic embeddings such that they also lie in a low-dimensional subspace. In particular, we consider the problem of learning a low-rank factorization of hyperbolic embeddings. We cast these problems as manifold optimization problems and propose computationally efficient algorithms. Empirical results illustrate the efficacy of the proposed approach.


page 1

page 2

page 3

page 4


Hyperbolic Manifold Regression

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

Tree! I am no Tree! I am a Low Dimensional Hyperbolic Embedding

Given data, finding a faithful low-dimensional hyperbolic embedding of t...

CO-SNE: Dimensionality Reduction and Visualization for Hyperbolic Data

Hyperbolic space can embed tree metric with little distortion, a desirab...

Joint Learning of Hyperbolic Label Embeddings for Hierarchical Multi-label Classification

We consider the problem of multi-label classification where the labels l...

Grassmannian Learning: Embedding Geometry Awareness in Shallow and Deep Learning

Modern machine learning algorithms have been adopted in a range of signa...

Learning Continuous Hierarchies in the Lorentz Model of Hyperbolic Geometry

We are concerned with the discovery of hierarchical relationships from l...

Low-Rank Representation over the Manifold of Curves

In machine learning it is common to interpret each data point as a vecto...