On clustering uncertain and structured data with Wasserstein barycenters and a geodesic criterion for the number of clusters

TL;DR

This paper introduces a clustering method for uncertain and structured data using Wasserstein barycenters and a geodesic criterion, effective in fields with complex data and significant observational errors.

Contribution

It proposes a novel clustering approach based on Wasserstein geometry and introduces a geodesic criterion for determining the optimal number of clusters.

Findings

Effective in clustering uncertain data in simulations

Successfully applied to bond yield curve clustering

Classified satellite image land uses accurately

Abstract

In this work clustering schemes for uncertain and structured data are considered relying on the notion of Wasserstein barycenters, accompanied by appropriate clustering indices based on the intrinsic geometry of the Wasserstein space where the clustering task is performed. Such type of clustering approaches are highly appreciated in many fields where the observational/experimental error is significant (e.g. astronomy, biology, remote sensing, etc.) or the data nature is more complex and the traditional learning algorithms are not applicable or effective to treat them (e.g. network data, interval data, high frequency records, matrix data, etc.). Under this perspective, each observation is identified by an appropriate probability measure and the proposed clustering schemes rely on discrimination criteria that utilize the geometric structure of the space of probability measures through core techniques from the optimal transport theory. The advantages and capabilities of the proposed approach and the geodesic criterion performance are illustrated through a simulation study and the implementation in two real world applications: (a) clustering eurozone countries according to their observed government bond yield curves and (b) classifying the areas of a satellite image to certain land uses categories, a standard task in remote sensing.