EUVIMEDEUVIMED entdecken
Crossref

Blockchain Assisted Federated Learning Over Wireless Channels: Dynamic Resource Allocation and Client Scheduling

Xiumei Deng, Jun Li, Chuan Ma, Kang Wei, Long Shi, Ming Ding, Wen Chen, H. Vincent Poor

IEEE Transactions on Wireless Communications · 2023-05 · 22 (5) · 3537-3553

DOI: 10.1109/twc.2022.3219501 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Wireless Communications, 2023-05. Verfasst von Xiumei Deng und 7 weiteren Autor:innen. Die Arbeit wurde bisher 44-mal zitiert (Crossref) und nennt 44 Literaturangaben. Gefördert von: Chinese National Key Project, National Natural Science Foundation of China, Fundamental Research Funds for the Central Universities.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Blockchain technology has been extensively studied to enable distributed and tamper-proof data processing in federated learning (FL). Most existing blockchain assisted FL (BFL) frameworks have employed a third-party blockchain network to decentralize the model aggregation process. However, decentralized model aggregation is vulnerable to pooling and collusion attacks from the third-party blockchain network. Driven by this issue, we propose a novel BFL framework that features the integration of training and mining at the client side. To optimize the learning performance of FL, we propose to maximize the long-term time average (LTA) training data size under a constraint of LTA energy consumption. To this end, we formulate a joint optimization problem of training client selection and resource allocation (i.e., the transmit power and computation frequency at the client side), and solve the long-term mixed integer non-linear program based on a Lyapunov technique. In particular, the proposed dynamic resource allocation and client scheduling (DRACS) algorithm can achieve a trade-off of [ $\mathcal {O}(1/V)$ , $\mathcal {O}(\sqrt {V})$ ] to balance the maximization of the LTA training data size and the minimization of the LTA energy consumption with a control parameter $V$ . Our experimental results show that the proposed DRACS algorithm achieves better learning accuracy than benchmark client scheduling strategies with limited time or energy consumption.

Förderung

  • Chinese National Key Project
  • National Natural Science Foundation of China
  • Fundamental Research Funds for the Central Universities
  • Future Network Grant of Provincial Education Board in Jiangsu;
  • Zhejiang Lab Open Research
  • Jiangsu Specially-Appointed Professor Program 2021;
  • Shanghai Kewei
  • Pudong

Zitieren

APA

Deng, X., Li, J., Ma, C., Wei, K., Shi, L., Ding, M., Chen, W., & Poor, H. V. (2023). Blockchain Assisted Federated Learning Over Wireless Channels: Dynamic Resource Allocation and Client Scheduling. IEEE Transactions on Wireless Communications, 22(5), 3537-3553. https://doi.org/10.1109/twc.2022.3219501

Vancouver

Deng X, Li J, Ma C, Wei K, Shi L, Ding M, et al. Blockchain Assisted Federated Learning Over Wireless Channels: Dynamic Resource Allocation and Client Scheduling. IEEE Transactions on Wireless Communications. 2023;22(5):3537-3553. doi:10.1109/twc.2022.3219501

BibTeX
@article{Deng2023,
  author = {Deng, Xiumei and Li, Jun and Ma, Chuan and Wei, Kang and Shi, Long and Ding, Ming and Chen, Wen and Poor, H. Vincent},
  title = {Blockchain Assisted Federated Learning Over Wireless Channels: Dynamic Resource Allocation and Client Scheduling},
  journal = {IEEE Transactions on Wireless Communications},
  year = {2023},
  volume = {22},
  number = {5},
  pages = {3537--3553},
  doi = {10.1109/twc.2022.3219501}
}
Kostenlos starten →