EUVIMEDEUVIMED entdecken
Crossref

Wireless Distributed Learning: A New Hybrid Split and Federated Learning Approach

Xiaolan Liu, Yansha Deng, Toktam Mahmoodi

IEEE Transactions on Wireless Communications · 2023-04 · 22 (4) · 2650-2665

DOI: 10.1109/twc.2022.3213411 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Wireless Communications, 2023-04. Verfasst von Xiaolan Liu und 2 weiteren Autor:innen. Die Arbeit wurde bisher 147-mal zitiert (Crossref) und nennt 30 Literaturangaben. Gefördert von: European Union’s Horizon 2020 Research and Innovation Program, Primo-5G: Virtual Presence in Moving Objects, e.g. drones, through 5G, Engineering and Physical Sciences Research Council (EPSRC), U.K.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Cellular-connected unmanned aerial vehicle (UAV) with flexible deployment is foreseen to be a major part of the sixth generation (6G) networks. The UAVs connected to the base station (BS), as aerial users (UEs), could exploit machine learning (ML) algorithms to provide a wide range of advanced applications, like object detection and video tracking. Conventionally, the ML model training is performed at the BS, known as centralized learning (CL), which causes high communication overhead due to the transmission of large datasets, and potential concerns about UE privacy. To address this, distributed learning algorithms, including federated learning (FL) and split learning (SL), were proposed to train the ML models in a distributed manner via only sharing model parameters. FL requires higher computational resource on the UE side than SL, while SL has larger communication overhead when the local dataset is large. To effectively train an ML model considering the diversity of UEs with different computational capabilities and channel conditions, we first propose a novel distributed learning architecture, a hybrid split and federated learning (HSFL) algorithm by reaping the parallel model training mechanism of FL and the model splitting structure of SL. We then provide its convergence analysis under non-independent and identically distributed (non-IID) data with random UE selection scheme. By conducting experiments on training two ML models, Net and AlexNet, in wireless UAV networks, our results demonstrate that the HSFL algorithm achieves higher learning accuracy than FL and less communication overhead than SL under IID and non-IID data, and the learning accuracy of HSFL algorithm increases with the increasing number of the split training UEs. We further propose a Multi-Arm Bandit (MAB) based best channel (BC) and best 2-norm (BN2) (MAB-BC-BN2) UE selection scheme to select the UEs with better wireless channel quality and larger local model updates for model training in each round. Numerical results demonstrate it achieves higher learning accuracy than BC, MAB-BC and MAB-BN2 UE selection scheme under non-IID, Dirichlet-nonIID and Dirichlet-Imbalanced data.

Förderung

  • European Union’s Horizon 2020 Research and Innovation Program
  • Primo-5G: Virtual Presence in Moving Objects, e.g. drones, through 5G
  • Engineering and Physical Sciences Research Council (EPSRC), U.K
  • Innovate UK through the Project “Automation of Network edge Infrastructure and Applications with aRtificiAl intelligence (ANIARA)”

Zitieren

APA

Liu, X., Deng, Y., & Mahmoodi, T. (2023). Wireless Distributed Learning: A New Hybrid Split and Federated Learning Approach. IEEE Transactions on Wireless Communications, 22(4), 2650-2665. https://doi.org/10.1109/twc.2022.3213411

Vancouver

Liu X, Deng Y, Mahmoodi T. Wireless Distributed Learning: A New Hybrid Split and Federated Learning Approach. IEEE Transactions on Wireless Communications. 2023;22(4):2650-2665. doi:10.1109/twc.2022.3213411

BibTeX
@article{Liu2023,
  author = {Liu, Xiaolan and Deng, Yansha and Mahmoodi, Toktam},
  title = {Wireless Distributed Learning: A New Hybrid Split and Federated Learning Approach},
  journal = {IEEE Transactions on Wireless Communications},
  year = {2023},
  volume = {22},
  number = {4},
  pages = {2650--2665},
  doi = {10.1109/twc.2022.3213411}
}
Kostenlos starten →