Federated Fractional Gradient Descent With Adaptive Parameter Updates for Accelerated Convergence on Heterogeneous Data

Federated learning (FL) is a prominent machine learning (ML) framework that enables training a global model across distributed client devices without exposing their private data. However, traditional FL methods often face challenges in achieving fast convergence, particularly in heterogeneous or non-independent and identically distributed (non-IID) data environments. These issues arise primarily from inaccurate gradient estimation during the optimization process. To address these limitations, this article introduces an adaptive optimizer, federated fractional gradient descent with adaptive parameter updates (FedFGD-APUs). In particular, the proposed FedFGD-APU optimizer leverages fractional-order derivatives for efficient gradient computation. It employs an adaptive strategy to dynamically adjust fractional order, learning rate, and momentum to improve learning convergence and stability. We also develop a theoretical computational framework linking federated optimization with adaptive fractional derivatives, establishing the convergence of FedFGD-APU for nonconvex optimization settings with a convergence rate of $\mathcal {O}(1/T)$ . We conduct comprehensive experiments on MNIST, CIFAR-10, and NSL-KDD datasets to validate FedFGD-APU's effectiveness under both IID and non-IID data distributions. The experimental results demonstrate that FedFGD-APU significantly improves communication speedups and testing accuracy across heterogeneous data scenarios.

Authors

Institutions

Publication Details

Journal
IEEE Transactions on Cybernetics
Published
2026-11-17
DOI
https://doi.org/10.1109/tcyb.2026.3750279
Primary Topic
Privacy-Preserving Technologies in Data
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Federated Fractional Gradient Descent With Adaptive Parameter Updates for Accelerated Convergence on Heterogeneous Data

Md Palash Uddin, Kuo‐Hui Yeh, Jine Tang, Yong Xiang et al.
2 links
IEEE Transactions on Cybernetics
Privacy-Preserving Technologies in Data
article

Federated Fractional Gradient Descent With Adaptive Parameter Updates for Accelerated Convergence on Heterogeneous Data

Md Palash Uddin, Kuo‐Hui Yeh, Jine Tang, Yong Xiang, Yushu Zhang, Mahmudul Hasan
article en

Abstract

Federated learning (FL) is a prominent machine learning (ML) framework that enables training a global model across distributed client devices without exposing their private data. However, traditional FL methods often face challenges in achieving fast convergence, particularly in heterogeneous or non-independent and identically distributed (non-IID) data environments. These issues arise primarily from inaccurate gradient estimation during the optimization process. To address these limitations, this article introduces an adaptive optimizer, federated fractional gradient descent with adaptive parameter updates (FedFGD-APUs). In particular, the proposed FedFGD-APU optimizer leverages fractional-order derivatives for efficient gradient computation. It employs an adaptive strategy to dynamically adjust fractional order, learning rate, and momentum to improve learning convergence and stability. We also develop a theoretical computational framework linking federated optimization with adaptive fractional derivatives, establishing the convergence of FedFGD-APU for nonconvex optimization settings with a convergence rate of $\mathcal {O}(1/T)$ . We conduct comprehensive experiments on MNIST, CIFAR-10, and NSL-KDD datasets to validate FedFGD-APU's effectiveness under both IID and non-IID data distributions. The experimental results demonstrate that FedFGD-APU significantly improves communication speedups and testing accuracy across heterogeneous data scenarios.

IEEE Transactions on CyberneticsVol. PP
National Yang Ming Chiao Tung University (TW), Deakin University (AU), Hebei University of Technology (CN), Jiangxi University of Finance and Economics (CN)
Privacy-Preserving Technologies in Data
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon