Federated learning (FL) has become de facto framework for collaborative learning among edge devices with privacy concern. The core of the FL strategy is the use of stochastic …
J So, C He, CS Yang, S Li, Q Yu… - Proceedings of …, 2022 - proceedings.mlsys.org
Secure model aggregation is a key component of federated learning (FL) that aims at protecting the privacy of each user's individual model while allowing for their global …
S Liu, G Yu, R Yin, J Yuan, L Shen… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
In recent years, wireless federated learning (FL) has been proposed to support the mobile intelligent applications over the wireless network, which protects the data privacy and …
The traditional cloud-centric approach for Deep Learning (DL) requires training data to be collected and processed at a central server which is often challenging in privacy-sensitive …
Q Lan, Q Zeng, P Popovski, D Gündüz… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
We consider the scenario of inference at the wireless edge, in which devices are connected to an edge server and ask the server to carry out remote classification, that is, classify data …
X Liu, Y Deng, T Mahmoodi - ICC 2022-IEEE International …, 2022 - ieeexplore.ieee.org
The use of unmanned aerial vehicles (UAVs) as flying users provides various applications by exploiting machine learning (ML) algorithms. Recently, distributed learning algorithms …
X Chen, J Li, C Chakrabarti - 2021 IEEE Workshop on Signal …, 2021 - ieeexplore.ieee.org
Split learning is a promising privacy-preserving distributed learning scheme that has low computation requirement at the edge device but has the disadvantage of high …
S Yue, J Ren - Next Generation Multiple Access, 2024 - Wiley Online Library
Federated meta‐learning (FML) has emerged as a promising paradigm to cope with the data limitation and heterogeneity challenges in today's edge learning arena. However, its …
X Cai, X Mo, J Chen, J Xu - IEEE Wireless Communications …, 2020 - ieeexplore.ieee.org
Mobile edge learning is an emerging technique that enables distributed edge devices to collaborate in training shared machine learning (ML) models by exploiting their local data …