Affordable Access

Access to the full text

Unsupervised collaborative learning based on Optimal Transport theory

Authors
  • Ben-Bouazza, Fatima-Ezzahraa1
  • Bennani, Younès2
  • Cabanes, Guénaël3
  • Touzani, Abdelfettah4
  • 1 Université Sidi Mohamed Ben Abdellah, LAMA, LIPN UMR 7030 CNRS , (Morocco)
  • 2 LaMSN, La Maison des Sciences Numériques, USPN, LIPN UMR 7030 CNRS , (France)
  • 3 Université Sorbonne Paris Nord, LIPN UMR 7030 CNRS , (France)
  • 4 Université Sidi Mohamed Ben Abdellah, LAMA, Morocco , (Morocco)
Type
Published Article
Journal
Journal of Intelligent Systems
Publisher
De Gruyter
Publication Date
Jun 07, 2021
Volume
30
Issue
1
Pages
698–719
Identifiers
DOI: 10.1515/jisys-2020-0068
Source
De Gruyter
Keywords
Disciplines
  • Research Article
License
Green

Abstract

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.

Report this publication

Statistics

Seen <100 times