Personalized and Private Peer-to-Peer Machine Learning

Aurélien Bellet 1 Rachid Guerraoui 2 Mahsa Taziki 3 Marc Tommasi 1
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 : The rise of connected personal devices together with privacy concerns call for machine learning algorithms capable of leveraging the data of a large number of agents to learn personalized models under strong privacy requirements. In this paper, we introduce an efficient algorithm to address the above problem in a fully decentralized (peer-to-peer) and asynchronous fashion, with provable convergence rate. We show how to make the algorithm differentially private to protect against the disclosure of information about the personal datasets, and formally analyze the trade-off between utility and privacy. Our experiments show that our approach dramatically outperforms previous work in the non-private case, and that under privacy constraints, we can significantly improve over models learned in isolation.
Complete list of metadatas

Cited literature [39 references]  Display  Hide  Download

https://hal.inria.fr/hal-01745796
Contributor : Team Magnet <>
Submitted on : Wednesday, November 14, 2018 - 7:00:57 PM
Last modification on : Friday, March 22, 2019 - 1:36:32 AM
Long-term archiving on : Friday, February 15, 2019 - 4:38:08 PM

File

aistats18_supp.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01745796, version 1
  • ARXIV : 1705.08435

Citation

Aurélien Bellet, Rachid Guerraoui, Mahsa Taziki, Marc Tommasi. Personalized and Private Peer-to-Peer Machine Learning. AISTATS 2018 - 21st International Conference on Artificial Intelligence and Statistics, Apr 2018, Lanzarote, Spain. pp.1-20. ⟨hal-01745796⟩

Share

Metrics

Record views

66

Files downloads

62