Decentralized Collaborative Learning of Personalized Models over Networks

Paul Vanhaesebrouck 1 Aurélien Bellet 1 Marc Tommasi 1, 2
1 MAGNET - Machine Learning in Information Networks
Inria Lille - Nord Europe, CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189
Abstract : We consider a set of learning agents in a col-laborative peer-to-peer network, where each agent learns a personalized model according to its own learning objective. The question addressed in this paper is: how can agents improve upon their locally trained model by communicating with other agents that have similar objectives? We introduce and analyze two asynchronous gossip algorithms running in a fully decentralized manner. Our first approach , inspired from label propagation, aims to smooth pre-trained local models over the network while accounting for the confidence that each agent has in its initial model. In our second approach, agents jointly learn and propagate their model by making iterative updates based on both their local dataset and the behavior of their neighbors. Our algorithm to optimize this challenging objective in a decentralized way is based on ADMM.
Liste complète des métadonnées

Littérature citée [21 références]  Voir  Masquer  Télécharger
Contributeur : Team Magnet <>
Soumis le : mercredi 19 octobre 2016 - 11:43:03
Dernière modification le : mardi 3 juillet 2018 - 11:28:15


Fichiers produits par l'(les) auteur(s)


  • HAL Id : hal-01383544, version 1
  • ARXIV : 1610.05202



Paul Vanhaesebrouck, Aurélien Bellet, Marc Tommasi. Decentralized Collaborative Learning of Personalized Models over Networks. [Research Report] INRIA Lille. 2016. 〈hal-01383544〉



Consultations de la notice


Téléchargements de fichiers