Gradient and channel aware dynamic scheduling for over-the-air computation in federated edge learning systems
To satisfy the expected plethora of computation-heavy applications, federated edge learning
(FEEL) is a new paradigm featuring distributed learning to carry the capacities of low-latency …
(FEEL) is a new paradigm featuring distributed learning to carry the capacities of low-latency …
Analog over-the-air federated learning with real-world data
Z Chen, Z Li, J Xu - 2022 IEEE International Conference on …, 2022 - ieeexplore.ieee.org
Federated edge learning enables intelligence services to be deployed at the edge of future
wireless network. To address the limited spectral resource and constrained scalability …
wireless network. To address the limited spectral resource and constrained scalability …
One-bit over-the-air aggregation for communication-efficient federated edge learning
To mitigate the multi-access latency in federated edge learning, an efficient broadband
analog transmission scheme has been recently proposed, featuring the aggregation of …
analog transmission scheme has been recently proposed, featuring the aggregation of …
Adaptive transmission for edge learning via training loss estimation
With the large-scale deployment of intelligent Internet of things (IoT) devices and the
increasing need for computation support in wireless access networks, edge computing plays …
increasing need for computation support in wireless access networks, edge computing plays …
One bit aggregation for federated edge learning with reconfigurable intelligent surface: Analysis and optimization
H Li, R Wang, W Zhang, J Wu - IEEE Transactions on Wireless …, 2022 - ieeexplore.ieee.org
As one of the most popular and attractive frameworks for model training, federated edge
learning (FEEL) presents a new paradigm, which avoids direct data transmission by …
learning (FEEL) presents a new paradigm, which avoids direct data transmission by …
Bayesian aircomp with sign-alignment precoding for wireless federated learning
In this paper, we consider the problem of wireless federated learning based on sign
stochastic gradient descent (signSGD) algorithm via a multiple access channel. When …
stochastic gradient descent (signSGD) algorithm via a multiple access channel. When …
Transmission power control for over-the-air federated averaging at network edge
Over-the-air computation (AirComp) has emerged as a new analog power-domain non-
orthogonal multiple access (NOMA) technique for low-latency model/gradient-updates …
orthogonal multiple access (NOMA) technique for low-latency model/gradient-updates …
Spatial Convergence of Federated Learning in Large-Scale Cellular Networks
The deployment of federated learning in a wireless network, called federated edge learning
(FEEL), exploits low-latency access to distributed mobile data to efficiently train an AI model …
(FEEL), exploits low-latency access to distributed mobile data to efficiently train an AI model …
Joint superposition coding and training for federated learning over multi-width neural networks
This paper aims to integrate two synergetic technologies, federated learning (FL) and width-
adjustable slimmable neural network (SNN) architectures. FL preserves data privacy by …
adjustable slimmable neural network (SNN) architectures. FL preserves data privacy by …
LEAP: Optimization Hierarchical Federated Learning on Non-IID Data with Coalition Formation Game
J Lu, Y Chen, S Cao, L Chen, W Wang… - arXiv preprint arXiv …, 2024 - arxiv.org
Although Hierarchical Federated Learning (HFL) utilizes edge servers (ESs) to alleviate
communication burdens, its model performance will be degraded by non-IID data and …
communication burdens, its model performance will be degraded by non-IID data and …