Fused Gromov-Wasserstein distance for structured objects: theoretical foundations and mathematical properties - Archive ouverte HAL Access content directly
Preprints, Working Papers, ... Year : 2019

Fused Gromov-Wasserstein distance for structured objects: theoretical foundations and mathematical properties

Abstract

Optimal transport theory has recently found many applications in machine learning thanks to its capacity for comparing various machine learning objects considered as distributions. The Kantorovitch formulation, leading to the Wasserstein distance, focuses on the features of the elements of the objects but treat them independently, whereas the Gromov-Wasserstein distance focuses only on the relations between the elements, depicting the structure of the object, yet discarding its features. In this paper we propose to extend these distances in order to encode simultaneously both the feature and structure informations, resulting in the Fused Gromov-Wasserstein distance. We develop the mathematical framework for this novel distance, prove its metric and interpolation properties and provide a concentration result for the convergence of finite samples. We also illustrate and interpret its use in various contexts where structured objects are involved.

Dates and versions

hal-02174316 , version 1 (05-07-2019)

Identifiers

Cite

Titouan Vayer, Laetitia Chapel, Rémi Flamary, Romain Tavenard, Nicolas Courty. Fused Gromov-Wasserstein distance for structured objects: theoretical foundations and mathematical properties. 2019. ⟨hal-02174316⟩
266 View
0 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More