EUVIMEDEUVIMED entdecken
Crossref

Contributions Estimation in Federated Learning: A Comprehensive Experimental Evaluation

Yiwei Chen, Kaiyu Li, Guoliang Li, Yong Wang

Proceedings of the VLDB Endowment · 2024-04 · 17 (8) · 2077-2090

DOI: 10.14778/3659437.3659459 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the VLDB Endowment, online erschienen am 31.05.2024. Verfasst von Yiwei Chen und 3 weiteren Autor:innen. Die Arbeit wurde bisher 19-mal zitiert (Crossref) und nennt 86 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Federated Learning (FL) provides a privacy-preserving and decentralized approach to collaborative machine learning for multiple FL clients. The contribution estimation mechanism in FL is extensively studied within the database community, which aims to compute fair and reasonable contribution scores as incentives to motivate FL clients. However, designing such methods involves challenges in three aspects: effectiveness, robustness, and efficiency. Firstly, contribution estimation methods should utilize the data utility information of various client coalitions rather than that of individual clients to ensure effectiveness. Secondly, we should beware of adverse clients who may exploit tactics like data replication or label flipping. Thirdly, estimating contribution in FL can be time-consuming due to enumerating various client coalitions. Despite numerous proposed methods to address these challenges, each possesses distinct advantages and limitations based on specific settings. However, existing methods have yet to be thoroughly evaluated and compared in the same experimental framework. Therefore, a unified and comprehensive evaluation framework is necessary to compare these methods under the same experimental settings. This paper conducts an extensive survey of contribution estimation methods in FL and introduces a comprehensive framework to evaluate their effectiveness, robustness, and efficiency. Through empirical results, we present extensive observations, valuable discoveries, and an adaptable testing framework that can facilitate future research in designing and evaluating contribution estimation methods in FL.

Zitieren

APA

Chen, Y., Li, K., Li, G., & Wang, Y. (2024). Contributions Estimation in Federated Learning: A Comprehensive Experimental Evaluation. Proceedings of the VLDB Endowment, 17(8), 2077-2090. https://doi.org/10.14778/3659437.3659459

Vancouver

Chen Y, Li K, Li G, Wang Y. Contributions Estimation in Federated Learning: A Comprehensive Experimental Evaluation. Proceedings of the VLDB Endowment. 2024;17(8):2077-2090. doi:10.14778/3659437.3659459

BibTeX
@article{Chen2024,
  author = {Chen, Yiwei and Li, Kaiyu and Li, Guoliang and Wang, Yong},
  title = {Contributions Estimation in Federated Learning: A Comprehensive Experimental Evaluation},
  journal = {Proceedings of the VLDB Endowment},
  year = {2024},
  volume = {17},
  number = {8},
  pages = {2077--2090},
  doi = {10.14778/3659437.3659459}
}
Kostenlos starten →