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.
Complete list of metadatas

Cited literature [21 references]  Display  Hide  Download

https://hal.inria.fr/hal-01383544
Contributor : Team Magnet <>
Submitted on : Wednesday, October 19, 2016 - 11:43:03 AM
Last modification on : Tuesday, September 10, 2019 - 11:32:02 AM

File

main_arXiv.pdf
Files produced by the author(s)

Identifiers

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

Citation

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

Share

Metrics

Record views

371

Files downloads

226