Hi there!
This is Feng Yu, a second-year PhD student in computer science at the University of Exeter, under the supervision of Prof. Jia Hu and Prof. Geyong Min. My research interests are mainly federated learning, continual learning and edge intelligence.
My research is supported by China Scholarship Council and University of Exeter Scholarships.
I am open to discussing research ideas and seeking academic collaborations. Drop me email if interested!
My previous research works cover several issues : federated learning, blokchain, generative adversarial network, differential privacy and privacy protection. Currently, I am interested in variety of approaches for federated learning
(Federated Graph Machine Learning, Federated Continual Learning, etc.) and related applications.
@article{YU202255,title={Blockchain-empowered secure federated learning system: Architecture and applications},journal={Computer Communications},volume={196},pages={55-65},year={2022},issn={0140-3664},doi={https://doi.org/10.1016/j.comcom.2022.09.008},url={https://www.sciencedirect.com/science/article/pii/S0140366422003474},author={Yu, Feng and Lin, Hui and Wang, Xiaoding and Yassine, Abdussalam and Hossain, M. Shamim},html={https://doi.org/10.1016/j.comcom.2022.09.008},pdf={bfl_comcom2022.pdf},bibtex_show={true},abbr={COMCOM},selected={true}}
Communication-Efficient Personalized Federated Meta-Learning in Edge Networks
Feng Yu
,
Hui Lin,
Xiaoding Wang,
Sahil Garg,
Georges Kaddoum,
Satinder Singh,
and Mohammad Mehedi Hassan
IEEE Transactions on Network and Service Management
2023
@article{yu_communication-efficient_2023,title={Communication-Efficient Personalized Federated Meta-Learning in Edge Networks},copyright={4.758},issn={1932-4537},doi={10.1109/TNSM.2023.3263831},journal={IEEE Transactions on Network and Service Management},author={Yu, Feng and Lin, Hui and Wang, Xiaoding and Garg, Sahil and Kaddoum, Georges and Singh, Satinder and Hassan, Mohammad Mehedi},year={2023},pages={1--1},html={https://doi.org/10.1109/tnsm.2023.3263831},bibtex_show={true},abbr={TNSM},selected={true}}
