Federated learning (FL) as a promising edge-learning framework can effectively address the latency and privacy issues by featuring distributed learning at the devices and model …
The rapid growth in storage capacity and computational power of mobile devices is making it increasingly attractive for devices to process data locally instead of risking privacy by …
Z Lin, H Liu, YJA Zhang - 2021 IEEE Globecom Workshops …, 2021 - ieeexplore.ieee.org
Federated learning (FL) has recently emerged as a promising technology to enable artificial intelligence (AI) at the network edge. To improve the communication efficiency of FL, over …
H Liu, X Yuan, YJA Zhang - 2021 IEEE International …, 2021 - ieeexplore.ieee.org
To exploit massive amounts of data at mobile edge networks, federated learning (FL) has been proposed as an attractive substitute for centralized machine learning. To improve the …
Y Sun, Z Lin, Y Mao, S Jin… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Federated learning (FL) is a popular privacy-preserving distributed training scheme, where multiple devices collaborate to train machine learning models by uploading local model …
Federated learning (FL) has been recognized as a viable distributed learning paradigm which trains a machine learning model collaboratively with massive mobile devices in the …
X Lin, Y Liu, F Chen - 2021 IEEE/CIC International Conference …, 2021 - ieeexplore.ieee.org
As a popular distributed machine learning based on stochastic gradient decent (SGD), federated learning enables edge devices to compute stochastic gradients and then upload …
T Sery, N Shlezinger, K Cohen… - GLOBECOM 2020-2020 …, 2020 - ieeexplore.ieee.org
Federated learning (FL) is a framework for distributed learning of centralized models. In FL, a set of edge devices train a model using their local data, while repeatedly exchanging their …
X Ma, H Sun, Q Wang, RQ Hu - 2021 IEEE 94th Vehicular …, 2021 - ieeexplore.ieee.org
A new machine learning (ML) technique termed as federated learning (FL) aims to preserve data at the edge devices and to only exchange ML model parameters in the learning …