Skip to Main content Skip to Navigation
Journal articles

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.
Document type :
Journal articles
Complete list of metadatas

Cited literature [78 references]  Display  Hide  Download
Contributor : Rémi Flamary <>
Submitted on : Tuesday, October 20, 2020 - 1:05:57 PM
Last modification on : Thursday, October 22, 2020 - 3:31:00 AM


Publisher files allowed on an open archive


Distributed under a Creative Commons Attribution 4.0 International License



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⟩



Record views


Files downloads