EUVIMEDEUVIMED entdecken
Crossref

Stochastic Coded Federated Learning: Theoretical Analysis and Incentive Mechanism Design

Yuchang Sun, Jiawei Shao, Yuyi Mao, Songze Li, Jun Zhang

IEEE Transactions on Wireless Communications · 2024-06 · 23 (6) · 6623-6638

DOI: 10.1109/twc.2023.3334732 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Wireless Communications, 2024-06. Verfasst von Yuchang Sun und 4 weiteren Autor:innen. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 47 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Federated learning (FL) has achieved great success as a privacy-preserving distributed training paradigm, where many edge devices collaboratively train a machine learning model by sharing the model updates instead of the raw data with a server. However, the heterogeneous computational and communication resources of edge devices give rise to stragglers that significantly decelerate the training process. To mitigate this issue, we propose a novel FL framework named stochastic coded federated learning (SCFL) that leverages coded computing techniques. In SCFL, before the training process starts, each edge device uploads a privacy-preserving coded dataset to the server, which is generated by adding Gaussian noise to the projected local dataset. During training, the server computes gradients on the global coded dataset to compensate for the missing model updates of the straggling devices. We design a gradient aggregation scheme to ensure that the aggregated model update is an unbiased estimate of the desired global update. Moreover, this aggregation scheme enables periodical model averaging to improve the training efficiency. We characterize the tradeoff between the convergence performance and privacy guarantee of SCFL. In particular, a more noisy coded dataset provides stronger privacy protection for edge devices but results in learning performance degradation. We further develop a contract-based incentive mechanism to coordinate such a conflict. The simulation results show that SCFL learns a better model within the given time and achieves a better privacy-performance tradeoff than the baseline methods. In addition, the proposed incentive mechanism grants better training performance than the conventional Stackelberg game approach.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Sun, Y., Shao, J., Mao, Y., Li, S., & Zhang, J. (2024). Stochastic Coded Federated Learning: Theoretical Analysis and Incentive Mechanism Design. IEEE Transactions on Wireless Communications, 23(6), 6623-6638. https://doi.org/10.1109/twc.2023.3334732

Vancouver

Sun Y, Shao J, Mao Y, Li S, Zhang J. Stochastic Coded Federated Learning: Theoretical Analysis and Incentive Mechanism Design. IEEE Transactions on Wireless Communications. 2024;23(6):6623-6638. doi:10.1109/twc.2023.3334732

BibTeX
@article{Sun2024,
  author = {Sun, Yuchang and Shao, Jiawei and Mao, Yuyi and Li, Songze and Zhang, Jun},
  title = {Stochastic Coded Federated Learning: Theoretical Analysis and Incentive Mechanism Design},
  journal = {IEEE Transactions on Wireless Communications},
  year = {2024},
  volume = {23},
  number = {6},
  pages = {6623--6638},
  doi = {10.1109/twc.2023.3334732}
}
Kostenlos starten →