Federated Learning and Privacy

Definitions of the terms and much more...  

Federated Learning and Privacy

By Kallista Bonawitz, Peter Kairouz, Brendan Mcmahan, Daniel Ramage

Communications of the ACM, April 2022, Vol. 65 No. 4, Pages 90-97  10.1145/3500240

Machine learning and data science are key tools in science, public policy, and the design of products and services thanks to the increasing affordability of collecting, storing, and processing large quantities of data. But centralized collection can expose individuals to privacy risks and organizations to legal risks if data is not properly managed. Starting with early work in 2016,13,15 an expanding community of researchers has explored how data ownership and provenance can be made first-class concepts in systems for learning and analytics in areas now known as federated learning (FL) and federated analytics (FA).

With this expanding community, interest has broadened from the initial work on federations of mobile devices to include FL across organizational silos, Internet of Things (IoT) devices, and more. In light of this, Kairouz et al.10 proposed a broader definition:

Federated learning is a machine learning setting where multiple entities (clients) 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.

An approach very similar in both philosophy and implementation, federated analytics17 can be taken to allow data scientists to generate analytical insight from the combined information in decentralized datasets. While the focus here is on FL, much of the discussion on technology and privacy applies equally well to FA use cases.

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.  ...... '