Federated Learning With Adaptive Aggregation Weights for Non-IID Data in Edge Networks

Xiaodong Li; Yulong Gao; Yansha Deng; Xinzhuo Jiang

doi:10.1109/TCCN.2025.3534248

Federated Learning With Adaptive Aggregation Weights for Non-IID Data in Edge Networks

Xiaodong Li, Yulong Gao^*, Yansha Deng, Xinzhuo Jiang

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

Abstract

Federated learning (FL) enables edge nodes to collaboratively train a global model under the coordination of a server without sharing local private data. However, data heterogeneity across nodes leads to serious performance degradation or even non-convergence of the learned model. To tackle this challenge, most existing methods typically involve either local model regularization or global model adjustments. Nevertheless, these methods primarily perform model aggregation based on the dataset size proportion, while the exploration of the impact of non-independent and identically distributed (non-IID) data on aggregation weights remains insufficient. To this end, we theoretically derive an analytical expression for the aggregation weights by minimizing the convergence upper bound of standard FL on non-IID data across nodes, achieving a tighter bound and superior convergence performance. Accordingly, we propose an adaptive aggregation weight strategy, called FedAAW. It can be easily incorporated into other FL methods to improve their convergence performance with negligible additional communication overhead. Extensive experiments on four common datasets show that FedAAW can effectively mitigate the performance degradation caused by data heterogeneity in various cases. Simply applying FedAAW to other methods can significantly improve their performance, achieving a maximum improvement of 37.32% in test accuracy and outperforming other state-of-the-art aggregation weight strategies.

Original language	English
Journal	IEEE Transactions on Cognitive Communications and Networking
DOIs	https://doi.org/10.1109/TCCN.2025.3534248
Publication status	Accepted/In press - 2025

Keywords

adaptive aggregation weight
edge networks
Federated learning
non-IID data

Access to Document

10.1109/TCCN.2025.3534248

Cite this

@article{3e0ec22e98184420aa1936ebffd6761a,

title = "Federated Learning With Adaptive Aggregation Weights for Non-IID Data in Edge Networks",

abstract = "Federated learning (FL) enables edge nodes to collaboratively train a global model under the coordination of a server without sharing local private data. However, data heterogeneity across nodes leads to serious performance degradation or even non-convergence of the learned model. To tackle this challenge, most existing methods typically involve either local model regularization or global model adjustments. Nevertheless, these methods primarily perform model aggregation based on the dataset size proportion, while the exploration of the impact of non-independent and identically distributed (non-IID) data on aggregation weights remains insufficient. To this end, we theoretically derive an analytical expression for the aggregation weights by minimizing the convergence upper bound of standard FL on non-IID data across nodes, achieving a tighter bound and superior convergence performance. Accordingly, we propose an adaptive aggregation weight strategy, called FedAAW. It can be easily incorporated into other FL methods to improve their convergence performance with negligible additional communication overhead. Extensive experiments on four common datasets show that FedAAW can effectively mitigate the performance degradation caused by data heterogeneity in various cases. Simply applying FedAAW to other methods can significantly improve their performance, achieving a maximum improvement of 37.32% in test accuracy and outperforming other state-of-the-art aggregation weight strategies.",

keywords = "adaptive aggregation weight, edge networks, Federated learning, non-IID data",

author = "Xiaodong Li and Yulong Gao and Yansha Deng and Xinzhuo Jiang",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE.",

year = "2025",

doi = "10.1109/TCCN.2025.3534248",

language = "English",

journal = "IEEE Transactions on Cognitive Communications and Networking",

issn = "2332-7731",

publisher = "IEEE",

}

TY - JOUR

T1 - Federated Learning With Adaptive Aggregation Weights for Non-IID Data in Edge Networks

AU - Li, Xiaodong

AU - Gao, Yulong

AU - Deng, Yansha

AU - Jiang, Xinzhuo

PY - 2025

Y1 - 2025

N2 - Federated learning (FL) enables edge nodes to collaboratively train a global model under the coordination of a server without sharing local private data. However, data heterogeneity across nodes leads to serious performance degradation or even non-convergence of the learned model. To tackle this challenge, most existing methods typically involve either local model regularization or global model adjustments. Nevertheless, these methods primarily perform model aggregation based on the dataset size proportion, while the exploration of the impact of non-independent and identically distributed (non-IID) data on aggregation weights remains insufficient. To this end, we theoretically derive an analytical expression for the aggregation weights by minimizing the convergence upper bound of standard FL on non-IID data across nodes, achieving a tighter bound and superior convergence performance. Accordingly, we propose an adaptive aggregation weight strategy, called FedAAW. It can be easily incorporated into other FL methods to improve their convergence performance with negligible additional communication overhead. Extensive experiments on four common datasets show that FedAAW can effectively mitigate the performance degradation caused by data heterogeneity in various cases. Simply applying FedAAW to other methods can significantly improve their performance, achieving a maximum improvement of 37.32% in test accuracy and outperforming other state-of-the-art aggregation weight strategies.

AB - Federated learning (FL) enables edge nodes to collaboratively train a global model under the coordination of a server without sharing local private data. However, data heterogeneity across nodes leads to serious performance degradation or even non-convergence of the learned model. To tackle this challenge, most existing methods typically involve either local model regularization or global model adjustments. Nevertheless, these methods primarily perform model aggregation based on the dataset size proportion, while the exploration of the impact of non-independent and identically distributed (non-IID) data on aggregation weights remains insufficient. To this end, we theoretically derive an analytical expression for the aggregation weights by minimizing the convergence upper bound of standard FL on non-IID data across nodes, achieving a tighter bound and superior convergence performance. Accordingly, we propose an adaptive aggregation weight strategy, called FedAAW. It can be easily incorporated into other FL methods to improve their convergence performance with negligible additional communication overhead. Extensive experiments on four common datasets show that FedAAW can effectively mitigate the performance degradation caused by data heterogeneity in various cases. Simply applying FedAAW to other methods can significantly improve their performance, achieving a maximum improvement of 37.32% in test accuracy and outperforming other state-of-the-art aggregation weight strategies.

KW - adaptive aggregation weight

KW - edge networks

KW - Federated learning

KW - non-IID data

UR - http://www.scopus.com/inward/record.url?scp=85216862887&partnerID=8YFLogxK

U2 - 10.1109/TCCN.2025.3534248

DO - 10.1109/TCCN.2025.3534248

M3 - Article

AN - SCOPUS:85216862887

SN - 2332-7731

JO - IEEE Transactions on Cognitive Communications and Networking

JF - IEEE Transactions on Cognitive Communications and Networking

ER -

Federated Learning With Adaptive Aggregation Weights for Non-IID Data in Edge Networks

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this