“Advances and Open Problems in Federated Learning” (2020), by Peter Kairouz et al. Computer Science research paper. Original abstract below, unchanged. A free PDF is available.

Advances and Open Problems in Federated Learning

Peter Kairouz, H. Brendan McMahan, Brendan Avent et al. · December 2, 2020 · Computer Science

Abstract

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.

Free PDF DOI: 10.1561/2200000083