Advances and Open Problems in Federated Learning - Inria EPFL Access content directly
Journal Articles Foundations and Trends in Machine Learning Year : 2021

Advances and Open Problems in Federated Learning

Peter Kairouz
  • Function : Author
Zachary Charles
  • Function : Author
Zachary Garrett
  • Function : Author
Adrià Gascón
  • Function : Author
Badih Ghazi
  • Function : Author
Ben Hutchinson
  • Function : Author
Jakub Konečný
  • Function : Author
Tancrède Lepoint
  • Function : Author
  • PersonId : 945702
Mehryar Mohri
  • Function : Author
Richard Nock
  • Function : Author
  • PersonId : 838976
Ayfer Ozgür
  • Function : Author
  • PersonId : 975379
Mariana Raykova
  • Function : Author
  • PersonId : 990432
Hang Qi
  • Function : Author
Daniel Ramage
  • Function : Author
Weikang Song
  • Function : Author
  • PersonId : 770450
  • IdRef : 182680304
Zheng Xu
  • Function : Author
Felix X. Yu
  • Function : Author
Sen Zhao
  • Function : Author

Abstract

Federated learning (FL) is a machine learning setting where many clients (e.g., mobile devices or whole organizations) collaboratively train a model under the orchestration of a central server (e.g., service provider), while keeping the training data decentralized. FL embodies the principles of focused data collection and minimization, and can mitigate many of the systemic privacy risks and costs resulting from traditional, centralized machine learning and data science approaches. Motivated by the explosive growth in FL research, this monograph discusses recent advances and presents an extensive collection of open problems and challenges.
Fichier principal
Vignette du fichier
1912.04977.pdf (1.35 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-02406503 , version 1 (12-12-2019)
hal-02406503 , version 2 (04-05-2021)

Identifiers

Cite

Peter Kairouz, Brendan H. Mcmahan, Brendan Avent, Aurélien Bellet, Mehdi Bennis, et al.. Advances and Open Problems in Federated Learning. Foundations and Trends in Machine Learning, 2021, 14 (1-2), pp.1-210. ⟨hal-02406503v2⟩
3087 View
13796 Download

Altmetric

Share

Gmail Facebook X LinkedIn More