X Liu, T Ratnarajah - arXiv preprint arXiv:2309.01816, 2023 - arxiv.org
Federated learning (FL) allows model training from local data by edge devices while preserving data privacy. However, the learning accuracy decreases due to the heterogeneity …
We consider the problem of convergence time minimization for federated learning (FL) implemented in wireless systems. In such setups, each wireless edge device transmits its …
P Li, G Cheng, X Huang, J Kang, R Yu… - IEEE Transactions …, 2023 - ieeexplore.ieee.org
Model update compression is a widely used technique to alleviate the communication cost in federated learning (FL). However, there is evidence indicating that the compression …
Z Chen, W Yi, S Lambotharan… - … 2023-2023 IEEE …, 2023 - ieeexplore.ieee.org
For wireless federated learning (FL), this work proposes an adaptive model pruning-based FL (AMP-FL) frame-work, where the edge server dynamically generates sub-models by …
Z Chen, W Yi, H Shin… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Most existing wireless federated learning (FL) studies focused on homogeneous model settings where devices train identical local models. In this setting, the devices with poor …
M Lan, Q Ling, S Xiao, W Zhang - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Federated learning (FL) enables multiple clients to collaborate on a common learning task via only exchanging model updates. With the progressive improvements in deep learning …
Federated learning (FL) has recently emerged as an attractive decentralized solution for wireless networks to collaboratively train a shared model while keeping data localized. As a …
The data heterogeneity across clients and the limited communication resources, eg, bandwidth and energy, are two of the main bottlenecks for wireless federated learning (FL) …
Due to the dynamics of wireless channels and limited wireless resources (ie, spectrum), deploying federated learning (FL) over wireless networks is challenged by frequent FL …