Machine learningPrivacy-preserving analysis
联邦学习
联邦学习（Federated Learning）是McMahan等人于2017年提出的一种分布式机器学习范式，其核心思想是在不将原始数据传输到中央服务器的情况下，通过多个去中心化客户端（如移动设备或医院系统）协作训练一个全局模型。每个参与方利用其私有数据在本地计算模型更新；只有这些更新（而非底层数据）被服务器通信和聚合，以改进共享模型。
阅读完整方法
仅限会员
登录使用免费账户登录即可阅读本节。
Method map
The neighbourhood of related methods — select a node to explore.
+4 more
来源
- McMahan, B., Moore, E., Ramage, D., Hampson, S., & Arcas, B. A. (2017). Communication-efficient learning of deep networks from decentralized data. Artificial Intelligence and Statistics, 1273–1282. link ↗
如何引用本页
ScholarGate. (2026, June 2). Federated Learning. ScholarGate. https://scholargate.app/zh/privacy/federated-learning
Which method?
Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.
Compare side by side →