Advances and Open Problems in Federated Learning
Peter Kairouz
(1)
,
Brendan H. Mcmahan
(1)
,
Brendan Avent
(2)
,
Aurélien Bellet
(3)
,
Mehdi Bennis
(4)
,
Arjun Nitin Bhagoji
(5)
,
Kallista Bonawitz
(1)
,
Zachary Charles
(1)
,
Graham Cormode
(6)
,
Rachel Cummings
(7)
,
Rafael Gregorio Lucas d'Oliveira
(8)
,
Salim El Rouayheb
(8)
,
David Evans
(9)
,
Josh Gardner
(10)
,
Zachary Garrett
(1)
,
Adrià Gascón
(1)
,
Badih Ghazi
(1)
,
Phillip B. Gibbons
(11)
,
Marco Gruteser
(1, 8)
,
Zaid Harchaoui
(10)
,
Chaoyang He
(2)
,
Lie He
(12)
,
Zhouyuan Huo
(13)
,
Ben Hutchinson
(1)
,
Justin Hsu
(14)
,
Martin Jaggi
(12)
,
Tara Javidi
(15)
,
Gauri Joshi
(11)
,
Mikhail Khodak
(11)
,
Jakub Konečný
(1)
,
Aleksandra Korolova
(2)
,
Farinaz Koushanfar
(15)
,
Sanmi Koyejo
(1, 16)
,
Tancrède Lepoint
(1)
,
Yang Liu
(17)
,
Prateek Mittal
(5)
,
Mehryar Mohri
(1)
,
Richard Nock
(18)
,
Ayfer Ozgür
(19)
,
Rasmus Pagh
(1, 20)
,
Mariana Raykova
(1)
,
Hang Qi
(1)
,
Daniel Ramage
(1)
,
Ramesh Raskar
(21)
,
Dawn Song
(22)
,
Weikang Song
(1)
,
Sebastian Urban Stich
(12)
,
Ziteng Sun
(23)
,
Ananda Theertha Suresh
(1)
,
Florian Tramèr
(19)
,
Praneeth Vepakomma
(21)
,
Jianyu Wang
(11)
,
Li Xiong
(24)
,
Zheng Xu
(1)
,
Qiang Yang
(25)
,
Felix X. Yu
(1)
,
Han Yu
(17)
,
Sen Zhao
(1)
1
Google Research
2 USC - University of Southern California
3 MAGNET - Machine Learning in Information Networks
4 CWC - Centre for Wireless Communications [University of Oulu]
5 Princeton University
6 University of Warwick [Coventry]
7 Georgia Institute of Technology [Atlanta]
8 Rutgers - Rutgers University System
9 University of Virginia
10 University of Washington [Seattle]
11 CMU - Carnegie Mellon University [Pittsburgh]
12 EPFL - Ecole Polytechnique Fédérale de Lausanne
13 PITT - University of Pittsburgh
14 University of Wisconsin-Madison
15 UC San Diego - University of California [San Diego]
16 UIUC - University of Illinois at Urbana-Champaign [Urbana]
17 NTU - Nanyang Technological University [Singapour]
18 ANU - Australian National University
19 Stanford University
20 ITU - IT University of Copenhagen
21 MIT - Massachusetts Institute of Technology
22 UC Berkeley - University of California [Berkeley]
23 Cornell University [New York]
24 Emory University [Atlanta, GA]
25 HKUST - Hong Kong University of Science and Technology
2 USC - University of Southern California
3 MAGNET - Machine Learning in Information Networks
4 CWC - Centre for Wireless Communications [University of Oulu]
5 Princeton University
6 University of Warwick [Coventry]
7 Georgia Institute of Technology [Atlanta]
8 Rutgers - Rutgers University System
9 University of Virginia
10 University of Washington [Seattle]
11 CMU - Carnegie Mellon University [Pittsburgh]
12 EPFL - Ecole Polytechnique Fédérale de Lausanne
13 PITT - University of Pittsburgh
14 University of Wisconsin-Madison
15 UC San Diego - University of California [San Diego]
16 UIUC - University of Illinois at Urbana-Champaign [Urbana]
17 NTU - Nanyang Technological University [Singapour]
18 ANU - Australian National University
19 Stanford University
20 ITU - IT University of Copenhagen
21 MIT - Massachusetts Institute of Technology
22 UC Berkeley - University of California [Berkeley]
23 Cornell University [New York]
24 Emory University [Atlanta, GA]
25 HKUST - Hong Kong University of Science and Technology
Aurélien Bellet
- Fonction : Auteur
- PersonId : 9877
- IdHAL : aurelien-bellet
- ORCID : 0000-0003-3440-1251
- IdRef : 17653136X
Mehdi Bennis
- Fonction : Auteur
- PersonId : 962378
Qiang Yang
- Fonction : Auteur
- PersonId : 765675
- ORCID : 0000-0003-4210-9007
Résumé
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.
| Origine | Fichiers produits par l'(les) auteur(s) |
|---|
