EUVIMEDEUVIMED entdecken
Crossref

Federated Learning and Privacy

Kallista Bonawitz, Peter Kairouz, Brendan McMahan, Daniel Ramage

Queue · 31.10.2021 · 19 (5) · 87-114

DOI: 10.1145/3494834.3500240 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Queue, online erschienen am 16.11.2021. Verfasst von Kallista Bonawitz und 3 weiteren Autor:innen. Die Arbeit wurde bisher 68-mal zitiert (Crossref) und nennt 19 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Centralized data collection can expose individuals to privacy risks and organizations to legal risks if data is not properly managed. Federated learning is a machine learning setting where multiple entities collaborate in solving a machine learning problem, under the coordination of a central server or service provider. Each client's raw data is stored locally and not exchanged or transferred; instead, focused updates intended for immediate aggregation are used to achieve the learning objective. This article provides a brief introduction to key concepts in federated learning and analytics with an emphasis on how privacy technologies may be combined in real-world systems and how their use charts a path toward societal benefit from aggregate statistics in new domains and with minimized risk to individuals and to the organizations who are custodians of the data.

Zitieren

APA

Bonawitz, K., Kairouz, P., McMahan, B., & Ramage, D. (2021). Federated Learning and Privacy. Queue, 19(5), 87-114. https://doi.org/10.1145/3494834.3500240

Vancouver

Bonawitz K, Kairouz P, McMahan B, Ramage D. Federated Learning and Privacy. Queue. 2021;19(5):87-114. doi:10.1145/3494834.3500240

BibTeX
@article{Bonawitz2021,
  author = {Bonawitz, Kallista and Kairouz, Peter and McMahan, Brendan and Ramage, Daniel},
  title = {Federated Learning and Privacy},
  journal = {Queue},
  year = {2021},
  volume = {19},
  number = {5},
  pages = {87--114},
  doi = {10.1145/3494834.3500240}
}
Kostenlos starten →