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

Titouan Vayer Laetita Chapel Rémi Flamary 1 Romain Tavenard 2 Nicolas Courty 3
2 LETG - Rennes - Littoral, Environnement, Télédétection, Géomatique
LETG - Littoral, Environnement, Télédétection, Géomatique UMR 6554
3 SEASIDE - SEarch, Analyze, Synthesize and Interact with Data Ecosystems
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, UBS - Université de Bretagne Sud
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.
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-02174316
Contributor : Nicolas Courty <>
Submitted on : Friday, July 5, 2019 - 9:14:59 AM
Last modification on : Sunday, July 7, 2019 - 1:34:03 AM

Links full text

Identifiers

  • HAL Id : hal-02174316, version 1
  • ARXIV : 1811.02834

Citation

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

Share

Metrics

Record views

18