ScholarGate
助手
Machine learningMachine learning

正则化联邦学习

正则化联邦学习在联邦学习框架的基础上，为每个客户端的局部目标函数增加了惩罚项，将局部更新锚定在更接近全局模型的位置。标准的实现——FedProx——增加了一个近邻项，用于控制任何单个客户端的漂移幅度，从而在客户端数据分布存在显著差异时提高收敛性和稳定性。

在 MethodMind 中打开即将推出视频即将推出Download slides

阅读完整方法

仅限会员

使用免费账户登录即可阅读本节。

登录

Method map

The neighbourhood of related methods — select a node to explore.

正则化联邦学习
联邦学习在线学习正则化梯度提升正则化逻辑回归半监督学习迁移学习

来源

  1. Li, T., Sahu, A. K., Zaheer, M., Sanjabi, M., Talwalkar, A., & Smith, V. (2020). Federated Optimization in Heterogeneous Networks. Proceedings of Machine Learning and Systems (MLSys), 2, 429–450. link ↗
  2. McMahan, B., Moore, E., Ramage, D., Hampson, S., & y Arcas, B. A. (2017). Communication-Efficient Learning of Deep Networks from Decentralized Data. Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (AISTATS), PMLR 54, 1273–1282. link ↗

如何引用本页

ScholarGate. (2026, June 3). Regularized Federated Learning (Proximal and Penalty-Based Approaches). ScholarGate. https://scholargate.app/zh/machine-learning/regularized-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 →

发现本页有问题？报告或提出修改建议 →

ScholarGate — Regularized Federated Learning (Regularized Federated Learning (Proximal and Penalty-Based Approaches)). 于 2026-06-15 检索自 https://scholargate.app/zh/machine-learning/regularized-federated-learning · 数据集： https://doi.org/10.5281/zenodo.20539026