HAL will be down for maintenance from Friday, June 10 at 4pm through Monday, June 13 at 9am. More information
Skip to Main content Skip to Navigation
Habilitation à diriger des recherches

Contributions to Decentralized and Privacy-Preserving Machine Learning

Aurélien Bellet 1
1 MAGNET - Machine Learning in Information Networks
Inria Lille - Nord Europe, CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189
Abstract : This manuscript presents, in a unified way, some of my contributions to the topic of decentralized and privacy-preserving machine learning. Decentralized learning, also known as federated learning, aims to allow a set of participants with local datasets to collaboratively train machine learning models while keeping their data decentralized. A key challenge in this context is to design decentralized algorithms that (i) can efficiently solve a variety of learning tasks on highly heterogeneous local datasets, and (ii) provide rigorous privacy guarantees while minimizing the impact on the utility of the learned models. To tackle these challenges, I describe three sets of contributions. First, I present a decentralized approach to collaboratively learn a personalized model for each user. Second, I address the problem of decentralized estimation and learning with pairwise loss functions. In both cases, privacy-preserving versions of these algorithms are introduced under the strong model of local differential privacy. Finally, to reduce the cost in utility induced by local differential privacy, I propose two approaches to improve the privacy-utility trade-offs of decentralized learning through appropriate relaxations of the local model.
Document type :
Habilitation à diriger des recherches
Complete list of metadata

https://tel.archives-ouvertes.fr/tel-03542802
Contributor : Aurélien Bellet Connect in order to contact the contributor
Submitted on : Tuesday, January 25, 2022 - 3:42:18 PM
Last modification on : Wednesday, March 23, 2022 - 3:51:23 PM
Long-term archiving on: : Tuesday, April 26, 2022 - 7:01:01 PM

File

HDR.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : tel-03542802, version 1

Citation

Aurélien Bellet. Contributions to Decentralized and Privacy-Preserving Machine Learning. Machine Learning [cs.LG]. Université de Lille, 2021. ⟨tel-03542802v1⟩

Share

Metrics

Record views

231

Files downloads

70