Advances and Open Problems in Federated Learning

作者：P. Kairouz, H. B. McMahan, Brendan Avent, A. Bellet, M. Bennis, A. Bhagoji, Keith Bonawitz, Zachary B. Charles, Graham Cormode, Rachel Cummings, Rafael G. L. D'Oliveira, S. E. Rouayheb, David Evans, Josh Gardner, Zachary Garrett, A. Gascón, Badih Ghazi, Phillip B. Gibbons, M. Gruteser, Z. Harchaoui, Chaoyang He, Lie He, Zhouyuan Huo, Ben Hutchinson, Justin Hsu, Martin Jaggi, T. Javidi, Gauri Joshi, M. Khodak, Jakub Konecný, A. Korolova, F. Koushanfar, Oluwasanmi Koyejo, Tancrède Lepoint, Yang Liu, Prateek Mittal, M. Mohri, R. Nock, A. Özgür, R. Pagh, Mariana Raykova, Hang Qi, Daniel Ramage, R. Raskar, D. Song, Weikang Song, Sebastian U. Stich, Ziteng Sun, A. Suresh, Florian Tramèr, Praneeth Vepakomma, Jianyu Wang, Li Xiong, Zheng Xu, Qiang Yang, Felix X. Yu, Han Yu, Sen Zhao · 发表于：Found. Trends Mach. Learn. · 年份：2019 · DOI：10.1561/2200000083 · 被引用次数：9424 · 研究领域：Computer Science、Mathematics

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 paper discusses recent advances and presents an extensive collection of open problems and challenges.