JZUS - Journal of Zhejiang University SCIENCE

Frontiers of Information Technology & Electronic Engineering

Accepted manuscript available online (unedited version)

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

Author(s): Tao SHEN¹, Zexi LI¹, Ziyu ZHAO¹, Didi ZHU¹, Zheqi LV¹, Kun KUANG¹, Shengyu ZHANG²^‡, Chao WU^3, ⁴^‡, Fei WU¹^‡
Affiliation(s): ¹College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China; more
Corresponding email(s): sy_zhang@zju.edu.cn, chao.wu@zju.edu.cn, wufei@zju.edu.cn
Key Words: Federated learning; Meta learning; Adaptive aggregation

Share this article to： More <<< Previous Paper \|Next Paper >>>

Tao SHEN¹, Zexi LI¹, Ziyu ZHAO¹, Didi ZHU¹, Zheqi LV¹, Kun KUANG¹, Shengyu ZHANG²^‡, Chao WU^3,⁴^‡, Fei WU¹^‡. FedMcon: an adaptive aggregation method for federated learning via meta controller[J]. Frontiers of Information Technology & Electronic Engineering,in press.https://doi.org/10.1631/FITEE.2400530

@article{title="FedMcon: an adaptive aggregation method for federated learning via meta controller",
author="Tao SHEN¹, Zexi LI¹, Ziyu ZHAO¹, Didi ZHU¹, Zheqi LV¹, Kun KUANG¹, Shengyu ZHANG²^‡, Chao WU^3,⁴^‡, Fei WU¹^‡",
journal="Frontiers of Information Technology & Electronic Engineering",
year="in press",
publisher="Zhejiang University Press & Springer",
doi="https://doi.org/10.1631/FITEE.2400530"
}

%0 Journal Article
%T FedMcon: an adaptive aggregation method for federated learning via meta controller
%A Tao SHEN¹
%A Zexi LI¹
%A Ziyu ZHAO¹
%A Didi ZHU¹
%A Zheqi LV¹
%A Kun KUANG¹
%A Shengyu ZHANG²^‡
%A Chao WU^3
%A⁴^‡
%A Fei WU¹^‡
%J Frontiers of Information Technology & Electronic Engineering
%P
%@ 2095-9184
%D in press
%I Zhejiang University Press & Springer
doi="https://doi.org/10.1631/FITEE.2400530"

TY - JOUR
T1 - FedMcon: an adaptive aggregation method for federated learning via meta controller
A1 - Tao SHEN¹
A1 - Zexi LI¹
A1 - Ziyu ZHAO¹
A1 - Didi ZHU¹
A1 - Zheqi LV¹
A1 - Kun KUANG¹
A1 - Shengyu ZHANG²^‡
A1 - Chao WU^{3
A1 -}⁴^‡
A1 - Fei WU¹^‡
J0 - Frontiers of Information Technology & Electronic Engineering
SP -
EP -
%@ 2095-9184
Y1 - in press
PB - Zhejiang University Press & Springer
ER -
doi="https://doi.org/10.1631/FITEE.2400530"

Abstract
Chinese Summary
Academic Network
Reviewer Comment

Abstract: Federated learning (FL) emerged as a novel machine learning setting that enables collaboratively training deep models on decentralized clients with privacy constraints. In vanilla federated learning algorithm (F_EDA_VG), the global model is generated by the weighted linear combination of local models, and the weights are proportional to the local data sizes. This methodology, however, encounters challenges when facing heterogeneous and unknown client data distributions, often leading to discrepancies from the intended global objective. The linear-combination-based aggregation often fails to address the varied dynamics presented by diverse scenarios, settings, and data distributions inherent in FL, resulting in hindered convergence and compromised generalization. In this paper, we presents a new aggregation method, FedMcon, in a framework of meta learning for FL. We introduce a learnable controller that trained on a small proxy dataset and served as the aggregator to learn how to adaptively aggregate heterogeneous local models into a better global model toward the desired objective. The experimental results indicate that the proposed method is effective in extremely non-i.i.d. data and it can simultaneously reach 8.5% generalization gain and 19 times communication speedup in one FL setting.

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference

Open peer comments: Debate/Discuss/Question/Opinion

<1>

- Go to

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference