Decentralized Collaborative Learning of Personalized Models over Networks - Université de Lille Accéder directement au contenu
Rapport (Rapport De Recherche) Année : 2016

Decentralized Collaborative Learning of Personalized Models over Networks

Résumé

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.
Fichier principal
Vignette du fichier
main_arXiv.pdf (580.69 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01383544 , version 1 (19-10-2016)

Identifiants

Citer

Paul Vanhaesebrouck, Aurélien Bellet, Marc Tommasi. Decentralized Collaborative Learning of Personalized Models over Networks. [Research Report] INRIA Lille. 2016. ⟨hal-01383544⟩
303 Consultations
158 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More