Gradient and channel aware dynamic scheduling for over-the-air computation in federated edge learning systems

J Du, B Jiang, C Jiang, Y Shi… - IEEE Journal on Selected …, 2023 - ieeexplore.ieee.org
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 …

Incentive-based federated learning for digital twin driven industrial mobile crowdsensing

B Li, Y Shi, Q Kong, Q Du, R Lu - IEEE Internet of Things …, 2023 - ieeexplore.ieee.org
Mobile crowdsensing has empowered the Industrial Internet of Things (IIoT) in many ways,
such as vehicle-aided traffic flow scheduling, drone-aided visual inspections, etc. However …

Subgradient descent learning over fading multiple access channels with over-the-air computation

TLS Gez, K Cohen - IEEE Access, 2023 - ieeexplore.ieee.org
We focus on a distributed learning problem in a communication network, consisting of
distributed nodes and a central parameter server (PS). The PS is responsible for performing …

Digital Over-the-Air Federated Learning in Multi-Antenna Systems

S Wang, M Chen, C Shen, C Yin, CG Brinton - arXiv preprint arXiv …, 2023 - arxiv.org
In this paper, the performance optimization of federated learning (FL), when deployed over a
realistic wireless multiple-input multiple-output (MIMO) communication system with digital …

A Dynamic Negative Log-Likelihood Optimization Method for Device Selection in Federated Learning with Over-The-Air Computation

J Ji, CT Lam, K Wang, BK Ng - 2023 9th International …, 2023 - ieeexplore.ieee.org
This paper addresses an optimization problem of device selections and aggregation errors
in over-the-air computation with federated learning (AirCompFL) systems. To achieve this …

QoS-Aware Computational Resource Allocation

J Du, C Jiang - Cooperation and Integration in 6G Heterogeneous …, 2022 - Springer
Recently, the boosting growth of computation-heavy applications raises great challenges for
the Fifth Generation (5G) and future wireless networks. As responding, the hybrid edge and …