Unsupervised collaborative learning based on Optimal Transport theory

Collaborative learning has recently achieved very significant results. It still suffers, however, from several issues, including the type of information that needs to be exchanged, the criteria for stopping and how to choose the right collaborators. We aim in this paper to improve the quality of the...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Ben-Bouazza Fatima-Ezzahraa, Bennani Younès, Cabanes Guénaël, Touzani Abdelfettah
Formato: article
Lenguaje:EN
Publicado: De Gruyter 2021
Materias:
Q
Acceso en línea:https://doaj.org/article/31948ad869ff4e72a682728e318471c6
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
Descripción
Sumario:Collaborative learning has recently achieved very significant results. It still suffers, however, from several issues, including the type of information that needs to be exchanged, the criteria for stopping and how to choose the right collaborators. We aim in this paper to improve the quality of the collaboration and to resolve these issues via a novel approach inspired by Optimal Transport theory. More specifically, the objective function for the exchange of information is based on the Wasserstein distance, with a bidirectional transport of information between collaborators. This formulation allows to learns a stopping criterion and provide a criterion to choose the best collaborators. Extensive experiments are conducted on multiple data-sets to evaluate the proposed approach.