This article lays out the general principles of federated learning, a decentralized and privacy protecting approach to statistical modeling.
Kallista Bonawitz, Peter Kairouz, Brendan McMahan, and Daniel Ramage. Federated Learning and Privacy: Building privacy-preserving systems for machine learning and data science on decentralized data, ACM Queue, 19(5), 2021-11-16. Available in html format or pdf format.