Advances and open problems in federated learning |
|
Author: | Kairouz, Peter1; McMahan, H. Brendan1; Avent, Brendan2; |
Organizations: |
1Google Research 2University of Southern California 3INRIA
4University of Oulu
5Princeton University 6University of Warwick 7Georgia Institute of Technology 8Rutgers University 9University of Virginia 10University of Washington 11Carnegie Mellon University 12Ecole Polytechnique Fédérale de Lausanne 13University of Pittsburgh 14University of Wisconsin–Madison 15University of California San Diego 16University of Illinois Urbana-Champaign 17Nanyang Technological University 18Australian National University 19Stanford University 20IT University of Copenhagen 21Massachusetts Institute of Technology 22University of California Berkeley 23Cornell University 24Emory University 25Hong Kong University of Science and Technology |
Format: | article |
Version: | accepted version |
Access: | open |
Online Access: | PDF Full Text (PDF, 0.9 MB) |
Persistent link: | http://urn.fi/urn:nbn:fi-fe2023022828866 |
Language: | English |
Published: |
Now Publishers,
2021
|
Publish Date: | 2023-02-28 |
Description: |
AbstractFederated 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. see all
|
Series: |
Foundations and trends in machine learning |
ISSN: | 1935-8237 |
ISSN-E: | 1935-8245 |
ISSN-L: | 1935-8237 |
Volume: | 14 |
Issue: | 1-2 |
Pages: | 1 - 210 |
DOI: | 10.1561/2200000083 |
OADOI: | https://oadoi.org/10.1561/2200000083 |
Type of Publication: |
A1 Journal article – refereed |
Field of Science: |
213 Electronic, automation and communications engineering, electronics |
Subjects: | |
Copyright information: |
© 2021 Peter Kairouz, H. Brendan McMahan, et al. The final publication is available from now publishers via http://dx.doi.org/10.1561/2200000083 |