Hierarchical federated learning ACROSS heterogeneous cellular networks

Warning The system is temporarily closed to updates for reporting purpose.

Salehi Heydar Abad, Mehdi and Özfatura, Mehmet Emre and Gündüz, Deniz and Erçetin, Özgür (2020) Hierarchical federated learning ACROSS heterogeneous cellular networks. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain

[img]PDF - Registered users only - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader

Official URL: http://dx.doi.org/10.1109/ICASSP40776.2020.9054634


We consider federated edge learning (FEEL), where mobile users (MUs) collaboratively learn a global model by sharing local updates on the model parameters rather than their datasets, with the help of a mobile base station (MBS). We optimize the resource allocation among MUs to reduce the communication latency in learning iterations. Observing that the performance in this centralized setting is limited due to the distance of the cell-edge users to the MBS, we introduce small cell base stations (SBSs) orchestrating FEEL among MUs within their cells, and periodically exchanging model updates with the MBS for global consensus. We show that this hierarchical federated learning (HFL) scheme significantly reduces the communication latency without sacrificing the accuracy.

Item Type:Papers in Conference Proceedings
Subjects:T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK5101-6720 Telecommunication
ID Code:40196
Deposited By:Özgür Erçetin
Deposited On:17 Sep 2020 12:34
Last Modified:17 Sep 2020 12:34

Repository Staff Only: item control page