Boning ZHANG
b.zhang.6@research.gla.ac.uk
Research title: Federated Learning for Heterogeneous Models with Knowledge Transfer: Algorithm Design and Performance Analysis
Research Summary
-
Federated Learning
-
Bayesian Learning
-
Differential Privacy
The University of Glasgow uses cookies for analytics. Find out more about our Privacy policy.
Necessary cookies enable core functionality. The website cannot function properly without these cookies, and can only be disabled by changing your browser preferences.
Analytical cookies help us improve our website. We use Google Analytics. All data is anonymised.
Clarity helps us to understand our users’ behaviour by visually representing their clicks, taps and scrolling. All data is anonymised.
b.zhang.6@research.gla.ac.uk
Research title: Federated Learning for Heterogeneous Models with Knowledge Transfer: Algorithm Design and Performance Analysis
Zhang, Boning, Liu, Dongzhu ORCID: https://orcid.org/0000-0001-7820-9531, Simeone, Osvaldo and Zhu, Guangxu
(2024)
Bayesian Over-the-Air FedAvg via Channel Driven Stochastic Gradient Langevin Dynamics.
In: IEEE Global Communications Conference (GLOBECOM 2023), Kuala Lumpur, Malaysia, 4–8 Dec 2023,
pp. 5286-5291.
ISBN 9798350310900
(doi: 10.1109/GLOBECOM54140.2023.10437650)
Zhang, Xiaokang, Zhang, Boning, Yu, Weikang and Kang, Xudong (2023) Federated deep learning with prototype matching for object extraction from very-high-resolution remote sensing images. IEEE Transactions on Geoscience and Remote Sensing, 61, 5603316. (doi: 10.1109/TGRS.2023.3244136)
Zhang, Xiaokang, Zhang, Boning, Yu, Weikang and Kang, Xudong (2023) Federated deep learning with prototype matching for object extraction from very-high-resolution remote sensing images. IEEE Transactions on Geoscience and Remote Sensing, 61, 5603316. (doi: 10.1109/TGRS.2023.3244136)
Zhang, Boning, Liu, Dongzhu ORCID: https://orcid.org/0000-0001-7820-9531, Simeone, Osvaldo and Zhu, Guangxu
(2024)
Bayesian Over-the-Air FedAvg via Channel Driven Stochastic Gradient Langevin Dynamics.
In: IEEE Global Communications Conference (GLOBECOM 2023), Kuala Lumpur, Malaysia, 4–8 Dec 2023,
pp. 5286-5291.
ISBN 9798350310900
(doi: 10.1109/GLOBECOM54140.2023.10437650)