Advances and Open Problems in Federated Learning
Advances and Open Problems in Federated Learning
复制标题
DOI：
10.1561/2200000083
复制
发表时间：
2021-01-01
影响因子：
32.8
通讯作者：
Zhao, Sen
中科院分区：
文献类型：
--
作者：
Kairouz, Peter;McMahan, H. Brendan;Zhao, Sen
联邦学习（FL）是一种机器学习设置，其中许多客户端（例如，移动设备或整个组织）在中央服务器（例如，服务提供商）的编排下协同训练模型，同时保持训练数据的分散。FL体现了集中数据收集和最小化的原则，可以减轻传统的集中式机器学习和数据科学方法带来的许多系统性隐私风险和成本。受FL研究爆炸式增长的推动，这本专著讨论了最近的进展，并提出了广泛的开放性问题和挑战。
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.