Non-iid data in federated learning: A systematic review with taxonomy, metrics, methods, frameworks and future directions

D Solans, M Heikkila, A Vitaletti, N Kourtellis… - arxiv preprint arxiv …, 2024 - arxiv.org
Recent advances in machine learning have highlighted Federated Learning (FL) as a
promising approach that enables multiple distributed users (so-called clients) to collectively …

An improved big data analytics architecture using federated learning for IoT-enabled urban intelligent transportation systems

S Kaleem, A Sohail, MU Tariq, M Asim - Sustainability, 2023 - mdpi.com
The exponential growth of the Internet of Things has precipitated a revolution in Intelligent
Transportation Systems, notably in urban environments. An ITS leverages advancements in …

Multi-UAV-assisted federated learning for energy-aware distributed edge training

J Tang, J Nie, Y Zhang, Z **ong… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Unmanned aerial vehicle (UAV)-assisted mobile edge computing (MEC) has largely
extended the border and capacity of artificial intelligence of things (AIoT) by providing a key …

Communication-efficient personalized federated meta-learning in edge networks

F Yu, H Lin, X Wang, S Garg… - … on Network and …, 2023 - ieeexplore.ieee.org
Due to the privacy breach risks and data aggregation of traditional centralized machine
learning (ML) approaches, applications, data and computing power are being pushed from …

A novel privacy-preserving graph convolutional network via secure matrix multiplication

HF Zhang, F Zhang, H Wang, C Ma, PC Zhu - Information Sciences, 2024 - Elsevier
Graph convolutional network (GCN) is one of the most representative methods in the realm
of graph neural networks (GNNs). In the convolution process, GCN combines the structural …

Corrfl: correlation-based neural network architecture for unavailability concerns in a heterogeneous iot environment

I Shaer, A Shami - IEEE Transactions on Network and Service …, 2023 - ieeexplore.ieee.org
The Federated Learning (FL) paradigm faces several challenges that limit its application in
real-world environments. These challenges include the local models' architecture …

Toward heterogeneous environment: Lyapunov-orientated imphetero reinforcement learning for task offloading

F Sun, Z Zhang, X Chang, K Zhu - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Task offloading combined with reinforcement learning (RL) is a promising research direction
in edge computing. However, the intractability in the training of RL and the heterogeneity of …

FedSW: Federated learning with adaptive sample weights

X Zhao, D Shen - Information Sciences, 2024 - Elsevier
Federated Learning (FL) is a machine learning approach in which a cluster of clients
collaboratively trains a model without sharing the data of any clients. As the datasets of each …

Privacy-preserving and communication-efficient stochastic alternating direction method of multipliers for federated learning

Y Zhang, Y Lu, F Liu, C Li, Z Gong, Z Hu, Q Xu - Information Sciences, 2025 - Elsevier
Federated learning constitutes a paradigm in distributed machine learning, wherein model
training unfolds through the exchange of intermediary results between a central server and …

Efficient privacy-preserving ML for IoT: Cluster-based split federated learning scheme for non-IID data

M Arafeh, M Wazzeh, H Sami, H Ould-Slimane… - Journal of Network and …, 2025 - Elsevier
In this paper, we propose a solution to address the challenges of varying client resource
capabilities in the IoT environment when using the SplitFed architecture for training models …