ScholarGate
助手
Machine learningMachine learning

鲁棒联邦学习

鲁棒联邦学习在标准联邦学习的基础上，增加了具有拜占庭容错能力的聚合规则，以保护全局模型免受恶意、损坏或不可靠客户端的影响。鲁棒聚合方法（如坐标中位数或 Krum）会过滤掉有害的更新，而不是简单地对客户端梯度进行平均，从而防止少数对抗性参与者破坏训练。

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.

鲁棒联邦学习
贝叶斯联邦学习联邦学习在线联邦学习鲁棒梯度提升半监督联邦学习迁移学习

来源

  1. Blanchard, P., El Mhamdi, E. M., Guerraoui, R., & Stainer, J. (2017). Machine Learning with Adversaries: Byzantine Tolerant Gradient Descent. Advances in Neural Information Processing Systems, 30. link ↗
  2. Yin, D., Chen, Y., Kannan, R., & Bartlett, P. (2018). Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates. Proceedings of the 35th International Conference on Machine Learning (ICML), PMLR 80:5650–5659. link ↗

如何引用本页

ScholarGate. (2026, June 3). Robust Federated Learning (Byzantine-Tolerant Distributed Training). ScholarGate. https://scholargate.app/zh/machine-learning/robust-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 — Robust Federated Learning (Robust Federated Learning (Byzantine-Tolerant Distributed Training)). 于 2026-06-15 检索自 https://scholargate.app/zh/machine-learning/robust-federated-learning · 数据集： https://doi.org/10.5281/zenodo.20539026