In cellular-based federated learning (FL), the base station (BS) is only used to aggregate parameters, which incurs a waste of computing resources at the BS. In this paper, a novel semi-federated learning (SemiFL) framework is proposed to break this bottleneck, where local devices simultaneously send their gradient updates and training samples to the BS for global model computation. To capture the performance of SemiFL over wireless networks, a closed-form convergence upper bound of SemiFL is derived. Then, a non-convex problem is formulated to improve the convergence behavior of SemiFL, subject to the transmit power, communication latency, and computation distortion. To solve this intractable problem, a two-stage algorithm is proposed by controlling the transmit power and receive beamformers. Numerical experiments validate that the proposed SemiFL framework can effectively improve accuracy and accelerate convergence as compared to conventional FL.
Semi-Federated Learning: An Integrated Framework for Pervasive Intelligence in 6G Networks / Zheng, J.; Ni, W.; Tian, H.; Gunduz, D.; Quek, T. Q. S.. - (2022), pp. 1-6. (Intervento presentato al convegno 2022 IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2022 tenutosi a usa nel 2022) [10.1109/INFOCOMWKSHPS54753.2022.9798021].
Semi-Federated Learning: An Integrated Framework for Pervasive Intelligence in 6G Networks
Gunduz D.;
2022
Abstract
In cellular-based federated learning (FL), the base station (BS) is only used to aggregate parameters, which incurs a waste of computing resources at the BS. In this paper, a novel semi-federated learning (SemiFL) framework is proposed to break this bottleneck, where local devices simultaneously send their gradient updates and training samples to the BS for global model computation. To capture the performance of SemiFL over wireless networks, a closed-form convergence upper bound of SemiFL is derived. Then, a non-convex problem is formulated to improve the convergence behavior of SemiFL, subject to the transmit power, communication latency, and computation distortion. To solve this intractable problem, a two-stage algorithm is proposed by controlling the transmit power and receive beamformers. Numerical experiments validate that the proposed SemiFL framework can effectively improve accuracy and accelerate convergence as compared to conventional FL.File | Dimensione | Formato | |
---|---|---|---|
Semi-Federated_Learning_An_Integrated_Framework_for_Pervasive_Intelligence_in_6G_Networks.pdf
Accesso riservato
Tipologia:
Versione pubblicata dall'editore
Dimensione
450.41 kB
Formato
Adobe PDF
|
450.41 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
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