FedMcon：一种通过元控制器实现的联邦学习自适应聚合方法

沈弢; 李则熹; 赵子瑜; 朱迪迪; 吕喆奇; 况琨; 张圣宇; 吴超; 吴飞

doi:10.1631/FITEE.2400530

Your Location：

Home >

Browse articles >

FedMcon：一种通过元控制器实现的联邦学习自适应聚合方法

常规文章 | Updated：2025-09-04

- FedMcon：一种通过元控制器实现的联邦学习自适应聚合方法
- FedMcon: an adaptive aggregation method for federated learning via meta controller^&
- “在联邦学习领域，提出了一种新的聚合方法FedMcon。专家研究人员引入了一种在小型代理数据集上训练的可学习控制器，并作为聚合器学习如何自适应地将异构局部模型聚合成更好的全局模型，以实现预期目标。这为解决联邦学习中收敛受阻和泛化能力受损的问题提供了解决方案。”
- 信息与电子工程前沿（英文） 2025年26卷第8期页码：1378-1393
- Affiliations：
  
  1.College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China
  2.School of Software Technology, Zhejiang University, Hangzhou 310027, China
  3.School of Public Affairs, Zhejiang University, Hangzhou 310027, China
  4.Academy of Social Governance, Zhejiang University, Hangzhou 310027, China
- Author bio：
  
  E-mail: tao.shen@zju.edu.cn
  zexi.li@zju.edu.cn
  ziyuzhao.cs@zju.edu.cn
  didi_zhu@zju.edu.cn
  zheqilv@zju.edu.cn
  kunkuang@zju.edu.cn
  ‡ Corresponding authors
- Funds：
  
  National Key Research and Development Program of China(2021ZD0110505);Zhejiang Provincial Key Research and Development Project, China(2023C01043);National Natural Science Foundation of China(62402429);Key Research and Development Program of Zhejiang Province, China(2024C03270);ZJU Kunpeng & Ascend Center of Excellence, and the Ningbo Yongjiang Talent Introduction Programme, China(2023A-397-G)
- DOI：10.1631/FITEE.2400530
  中图分类号： TP39
- 收稿：2024-06-20，
  
  修回：2024-12-15，
  
  纸质出版：2025-08
- Accepted：
Scan QR Code
沈弢, 李则熹, 赵子瑜, 等. FedMcon：一种通过元控制器实现的联邦学习自适应聚合方法[J]. 信息与电子工程前沿（英文）, 2025,26(8):1378-1393.

Tao SHEN, Zexi LI, Ziyu ZHAO, et al. FedMcon: an adaptive aggregation method for federated learning via meta controller^&[J]. Frontiers of Information Technology & Electronic Engineering, 2025, 26(8): 1378-1393.
沈弢, 李则熹, 赵子瑜, 等. FedMcon：一种通过元控制器实现的联邦学习自适应聚合方法[J]. 信息与电子工程前沿（英文）, 2025,26(8):1378-1393. DOI： 10.1631/FITEE.2400530.

Tao SHEN, Zexi LI, Ziyu ZHAO, et al. FedMcon: an adaptive aggregation method for federated learning via meta controller^&[J]. Frontiers of Information Technology & Electronic Engineering, 2025, 26(8): 1378-1393. DOI： 10.1631/FITEE.2400530.

浏览量

Downloads

CSCD

文章被引用时，请邮件提醒。

Submit

工具集

关联资源

Prototypical clustered federated learning for heart rate prediction

Federated deep reinforcement learning based computation offloading in a low Earth orbit satellite edge computing system

Federated learning on non-IID and long-tailed data via dual-decoupling

Communication efficiency optimization of federated learning for computing and network convergence of 6G networks

A survey of energy-efficient strategies for federated learning in mobile edge computing

FedMcon：一种通过元控制器实现的联邦学习自适应聚合方法

FedMcon: an adaptive aggregation method for federated learning via meta controller&

DOI：10.1631/FITEE.2400530

FedMcon: an adaptive aggregation method for federated learning via meta controller^&