Distributed learning is envisioned as the bedrock of next-generation intelligent networks, where intelligent agents, such as mobile devices, robots, and sensors, exchange information …
W Wu, M Li, K Qu, C Zhou, X Shen… - IEEE Journal on …, 2023 - ieeexplore.ieee.org
Split learning (SL) is a collaborative learning framework, which can train an artificial intelligence (AI) model between a device and an edge server by splitting the AI model into a …
D Yang, W Zhang, Q Ye, C Zhang… - IEEE Transactions …, 2023 - ieeexplore.ieee.org
In this paper, we present a three-layer (ie, device, field, and factory layers) deterministic federated learning (FL) framework, named DetFed, which accelerates collaborative learning …
X Cao, G Zhu, J Xu, Z Wang… - IEEE Journal on Selected …, 2021 - ieeexplore.ieee.org
Over-the-air federated edge learning (Air-FEEL) has emerged as a communication-efficient solution to enable distributed machine learning over edge devices by using their data locally …
X Cao, G Zhu, J Xu, S Cui - IEEE Journal on Selected Areas in …, 2022 - ieeexplore.ieee.org
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 …
Federated learning (FL) over mobile devices has fostered numerous intriguing applications/services, many of which are delay-sensitive. In this paper, we propose a service …
P Liu, J Jiang, G Zhu, L Cheng, W Jiang, W Luo… - Frontiers of Information …, 2022 - Springer
Training a machine learning model with federated edge learning (FEEL) is typically time consuming due to the constrained computation power of edge devices and the limited …
X Zhou, J Zhao, H Han, C Guet - 2022 IEEE 42nd International …, 2022 - ieeexplore.ieee.org
Federated Learning (FL) is an intriguing distributed machine learning approach due to its privacy-preserving characteristics. To balance the trade-off between energy and execution …
This paper considers improving wireless communication and computation efficiency in federated learning (FL) via model quantization. In the proposed bitwidth FL scheme, edge …