Federated Learning: Challenges, Methods, and Future Directions
Federated Learning: Challenges, Methods, and Future Directions
复制标题
DOI：
10.1109/msp.2020.2975749
复制
发表时间：
2020-05-01
影响因子：
14.9
通讯作者：
Smith, Virginia
中科院分区：
文献类型：
--
作者：
Li, Tian;Sahu, Anit Kumar;Smith, Virginia
联邦学习涉及通过远程设备或孤立的数据中心（例如手机或医院）训练统计模型，同时保持数据本地化。在异构和潜在的大规模网络中进行训练带来了新的挑战，需要从根本上偏离大规模机器学习、分布式优化和隐私保护数据分析的标准方法。在本文中，我们讨论了联邦学习的独特特征和挑战，对当前方法进行了广泛的概述，并概述了与广泛的研究社区相关的未来工作的几个方向。
Federated learning involves training statistical models over remote devices or siloed data centers, such as mobile phones or hospitals, while keeping data localized. Training in heterogeneous and potentially massive networks introduces novel challenges that require a fundamental departure from standard approaches for large-scale machine learning, distributed optimization, and privacy-preserving data analysis. In this article, we discuss the unique characteristics and challenges of federated learning, provide a broad overview of current approaches, and outline several directions of future work that are relevant to a wide range of research communities.