Elliptical Ordinal Embedding

TL;DR

This paper introduces a novel approach to ordinal embedding by representing objects as Gaussian distributions instead of points, capturing uncertainty and improving data structure representation.

Contribution

It proposes embedding objects as Gaussian distributions in ordinal embedding, offering advantages like uncertainty modeling and enhanced data structure capture.

Findings

Gaussian embeddings better reflect data uncertainty

Improved data structure representation demonstrated

Advantages shown on synthetic and real datasets

Abstract

Ordinal embedding aims at finding a low dimensional representation of objects from a set of constraints of the form "item $j$ is closer to item $i$ than item $k$". Typically, each object is mapped onto a point vector in a low dimensional metric space. We argue that mapping to a density instead of a point vector provides some interesting advantages, including an inherent reflection of the uncertainty about the representation itself and its relative location in the space. Indeed, in this paper, we propose to embed each object as a Gaussian distribution. We investigate the ability of these embeddings to capture the underlying structure of the data while satisfying the constraints, and explore properties of the representation. Experiments on synthetic and real-world datasets showcase the advantages of our approach. In addition, we illustrate the merit of modelling uncertainty, which enriches the visual perception of the mapped objects in the space.