Accéder directement au contenu Accéder directement à la navigation
Article dans une revue

Fused Gromov-Wasserstein Distance for Structured Objects

Abstract : Optimal transport theory has recently found many applications in machine learning thanks to its capacity to meaningfully compare various machine learning objects that are viewed as distributions. The Kantorovitch formulation, leading to the Wasserstein distance, focuses on the features of the elements of the objects, but treats them independently, whereas the Gromov–Wasserstein distance focuses on the relations between the elements, depicting the structure of the object, yet discarding its features. In this paper, we study the Fused Gromov-Wasserstein distance that extends the Wasserstein and Gromov–Wasserstein distances in order to encode simultaneously both the feature and structure information. We provide the mathematical framework for this distance in the continuous setting, 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 applications, where structured objects are involved.
Type de document :
Article dans une revue
Liste complète des métadonnées

Littérature citée [78 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-02971153
Contributeur : Rémi Flamary <>
Soumis le : mardi 20 octobre 2020 - 13:05:57
Dernière modification le : lundi 30 novembre 2020 - 15:10:05

Fichier

algorithms-13-00212-v2.pdf
Fichiers éditeurs autorisés sur une archive ouverte

Licence


Distributed under a Creative Commons Paternité 4.0 International License

Identifiants

Citation

Titouan Vayer, Laetitia Chapel, Rémi Flamary, Romain Tavenard, Nicolas Courty. Fused Gromov-Wasserstein Distance for Structured Objects. Algorithms, MDPI, 2020, 13 (9), pp.212. ⟨10.3390/a13090212⟩. ⟨hal-02971153⟩

Partager

Métriques

Consultations de la notice

64

Téléchargements de fichiers

56