EUVIMEDEUVIMED entdecken
Crossref

Reputation-aware Revenue Allocation for Auction-based Federated Learning

Xiaoli Tang, Han Yu

Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (19) · 20832-20840

DOI: 10.1609/aaai.v39i19.34296 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Xiaoli Tang und 1 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Auction-based Federated Learning (AFL) has gained significant research interest due to its ability to incentivize data owners (DOs) to participate in FL model training tasks of data consumers (DCs) through economic mechanisms via the auctioneer. One of the critical research issues in AFL is decision support for the auctioneer. Existing approaches are based on the simplified assumption of a single, monopolistic AFL marketplace, which is unrealistic in real-world scenarios where multiple AFL marketplaces can co-exist and compete for the same pool of DOs. In this paper, we relax this assumption and frame the AFL auctioneer decision support problem from the perspective of helping them attract participants in a competitive AFL marketplace environment while safeguarding profit. To achieve this objective, we propose the Auctioneer Revenue Allocation Strategy for AFL (ARAS-AFL). We design the concepts of the attractiveness and competitiveness from the perspective of autioneer reputation. Based on the Lyapunov optimization, ARAS-AFL helps individual AFL auctioneer achieve the dual objective of balancing the reputation management costs and its own profit by designing a dynamic revenue allocation strategy. It takes into account both the auctioneer’s revenue and the changes in the number of participants on the AFL marketplace. Through extensive experiments on widely used benchmark datasets, ARAS-AFL demonstrates superior performance compared to state-of-the-art approaches. It outperforms the best baseline by 49.06%, 98.69%, 10.32%, and 4.77% in terms of total revenue, number of data owners, public reputation and accuracy of federated learning models, respectively.

Zitieren

APA

Tang, X., & Yu, H. (2025). Reputation-aware Revenue Allocation for Auction-based Federated Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 39(19), 20832-20840. https://doi.org/10.1609/aaai.v39i19.34296

Vancouver

Tang X, Yu H. Reputation-aware Revenue Allocation for Auction-based Federated Learning. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(19):20832-20840. doi:10.1609/aaai.v39i19.34296

BibTeX
@article{Tang2025,
  author = {Tang, Xiaoli and Yu, Han},
  title = {Reputation-aware Revenue Allocation for Auction-based Federated Learning},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2025},
  volume = {39},
  number = {19},
  pages = {20832--20840},
  doi = {10.1609/aaai.v39i19.34296}
}
Kostenlos starten →