Inicio  /  Algorithms  /  Vol: 13 Par: 9 (2020)  /  Artículo
ARTÍCULO
TITULO

Fused Gromov-Wasserstein Distance for Structured Objects

Titouan Vayer    
Laetitia Chapel    
Remi Flamary    
Romain Tavenard and Nicolas Courty    

Resumen

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.

 Artículos similares

       
 
Juan Gavala-González, Mª Elena Porras-García, José Carlos Fernández-García and Mateo Real-Pérez    
The main purpose of this study was to study the effects of a specific rowing ergometer training program on the athletic performance of young adolescents (N = 56; 11.73 ± 1.4 years old) compared to a workout based on general strength training. An eight-we... ver más
Revista: Applied Sciences

 
Pornrawee Tatit, Kiki Adhinugraha and David Taniar    
Using spatial data in mobile applications has grown significantly, thereby empowering users to explore locations, navigate unfamiliar areas, find transportation routes, employ geomarketing strategies, and model environmental factors. Spatial databases ar... ver más
Revista: Algorithms

 
Nenad Marku? and Mirko Su?njevic    
Recently, there has been renewed interest in signed distance bound representations due to their unique properties for 3D shape modelling. This is especially the case for deep learning-based bounds. However, it is beneficial to work with polygons in most ... ver más
Revista: Algorithms

 
Shahbaz Sikandar, Rabbia Mahum and AbdulMalik Alsalman    
The multimedia content generated by devices and image processing techniques requires high computation costs to retrieve images similar to the user?s query from the database. An annotation-based traditional system of image retrieval is not coherent becaus... ver más
Revista: Applied Sciences

 
Ayse Yavuz Ozalp, Halil Akinci and Mustafa Zeybek    
The Eastern Black Sea Region is regarded as the most prone to landslides in Turkey due to its geological, geographical, and climatic characteristics. Landslides in this region inflict both fatalities and significant economic damage. The main objective of... ver más
Revista: Water