EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Enhancing Convergence in Federated Learning: A Contribution-Aware Asynchronous Approach

Changxin Xu, Yuxin Qiao, Zhanxin Zhou, Fanghao Ni, Jize Xiong

Computer Life · 2024

DOI: 10.54097/646rv696 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computer Life, 2024. Verfasst von Changxin Xu und 4 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Federated Learning (FL) is a distributed machine learning paradigm that allows clients to train models on their data while preserving their privacy. FL algorithms, such as Federated Averaging (FedAvg) and its variants, have been shown to converge well in many scenarios. However, these methods require clients to upload their local updates to the server in a synchronous manner, which can be slow and unreliable in realistic FL settings. To address this issue, researchers have developed asynchronous FL methods that allow clients to continue training on their local data using a stale global model. However, most of these methods simply aggregate all of the received updates without considering their relative contributions, which can slow down convergence. In this paper, we propose a contribution-aware asynchronous FL method that takes into account the staleness and statistical heterogeneity of the received updates. Our method dynamically adjusts the contribution of each update based on these factors, which can speed up convergence compared to existing methods.

Zitieren

APA

Xu, C., Qiao, Y., Zhou, Z., Ni, F., & Xiong, J. (2024). Enhancing Convergence in Federated Learning: A Contribution-Aware Asynchronous Approach. Computer Life. https://doi.org/10.54097/646rv696

Vancouver

Xu C, Qiao Y, Zhou Z, Ni F, Xiong J. Enhancing Convergence in Federated Learning: A Contribution-Aware Asynchronous Approach. Computer Life. 2024. doi:10.54097/646rv696

BibTeX
@article{Xu2024,
  author = {Xu, Changxin and Qiao, Yuxin and Zhou, Zhanxin and Ni, Fanghao and Xiong, Jize},
  title = {Enhancing Convergence in Federated Learning: A Contribution-Aware Asynchronous Approach},
  journal = {Computer Life},
  year = {2024},
  doi = {10.54097/646rv696}
}
Kostenlos starten →