Federated learning (FL) over wireless communication channels, specifically, over-the-air (OTA) model aggregation framework is considered. In OTA wireless setups, the adverse channel effects can be alleviated by increasing the number of receive antennas at the parameter server (PS), which performs model aggregation. However, the performance of OTA FL is severely limited by the presence of mobile users (MUs) located far away from the PS. In this paper, to mitigate this limitation, we propose hierarchical over-the-air federated learning (HOTAFL), which utilizes intermediary servers (IS) to form clusters near MUs. We provide a convergence analysis for the proposed setup, and demonstrate through experimental results that local aggregation in each cluster before global aggregation leads to a better performance and faster convergence than OTA FL.
Hierarchical Over-the-Air Federated Edge Learning / Aygun, O.; Kazemi, M.; Gunduz, D.; Duman, T. M.. - 2022-:(2022), pp. 3376-3381. (Intervento presentato al convegno 2022 IEEE International Conference on Communications, ICC 2022 tenutosi a COEX, kor nel 2022) [10.1109/ICC45855.2022.9839230].
Hierarchical Over-the-Air Federated Edge Learning
Gunduz D.;
2022
Abstract
Federated learning (FL) over wireless communication channels, specifically, over-the-air (OTA) model aggregation framework is considered. In OTA wireless setups, the adverse channel effects can be alleviated by increasing the number of receive antennas at the parameter server (PS), which performs model aggregation. However, the performance of OTA FL is severely limited by the presence of mobile users (MUs) located far away from the PS. In this paper, to mitigate this limitation, we propose hierarchical over-the-air federated learning (HOTAFL), which utilizes intermediary servers (IS) to form clusters near MUs. We provide a convergence analysis for the proposed setup, and demonstrate through experimental results that local aggregation in each cluster before global aggregation leads to a better performance and faster convergence than OTA FL.File | Dimensione | Formato | |
---|---|---|---|
2112.11167.pdf
Open access
Tipologia:
Versione dell'autore revisionata e accettata per la pubblicazione
Dimensione
3.53 MB
Formato
Adobe PDF
|
3.53 MB | Adobe PDF | Visualizza/Apri |
Pubblicazioni consigliate
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris