EUVIMEDEUVIMED entdecken
Crossref

A Profit-Maximizing Data Marketplace with Differentially Private Federated Learning under Price Competition

Peng Sun, Liantao Wu, Zhibo Wang, Jinfei Liu, Juan Luo, Wenqiang Jin

Proceedings of the ACM on Management of Data · 01.10.2024 · 2 (4) · 1-27

DOI: 10.1145/3677127 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the ACM on Management of Data, online erschienen am 30.09.2024. Verfasst von Peng Sun und 5 weiteren Autor:innen. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 53 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Hunan Province, Young Elite Scientists Sponsorship Program by CAST.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The proliferation of machine learning (ML) applications has given rise to a new and popular data marketplace paradigm. These marketplaces facilitate ML model requesters in obtaining data from data owners to train their desired models. To mitigate the privacy concerns of data owners, federated learning (FL) has been introduced, enabling collaborative model training without raw data trading. Furthermore, researchers have incorporated differential privacy (DP) techniques into FL, resulting in differentially private federated learning (DPFL) to enhance privacy preservation. However, existing designs of DPFL-based data marketplaces consider a simplified but unrealistic scenario where the model requester holds dominant market power, and data owners cannot set their own prices. In this work, we propose a novel DPFL-based data marketplace that accommodates both price-taking and price-setting data owners. We model the interactions among the model requester and these two types of data owners as a three-stage Stackelberg game, focusing on maximizing the model requester's profit. We rigorously establish that the formulated game is a convex game with a unique subgame perfect equilibrium. Moreover, we devise iterative algorithms to determine the equilibrium strategies for the model requester and price-setting data owners. Notably, our algorithms allow data owners to operate without requiring complete information about the model requester or other data owners. Numerical experiments demonstrate the superiority of our proposed three-stage framework in terms of the model requester's profitability compared to scenarios where only price-taking data owners are involved. Furthermore, we reveal that price competition among price-setting data owners reduces equilibrium market prices.

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Hunan Province
  • Young Elite Scientists Sponsorship Program by CAST

Zitieren

APA

Sun, P., Wu, L., Wang, Z., Liu, J., Luo, J., & Jin, W. (2024). A Profit-Maximizing Data Marketplace with Differentially Private Federated Learning under Price Competition. Proceedings of the ACM on Management of Data, 2(4), 1-27. https://doi.org/10.1145/3677127

Vancouver

Sun P, Wu L, Wang Z, Liu J, Luo J, Jin W. A Profit-Maximizing Data Marketplace with Differentially Private Federated Learning under Price Competition. Proceedings of the ACM on Management of Data. 2024;2(4):1-27. doi:10.1145/3677127

BibTeX
@article{Sun2024,
  author = {Sun, Peng and Wu, Liantao and Wang, Zhibo and Liu, Jinfei and Luo, Juan and Jin, Wenqiang},
  title = {A Profit-Maximizing Data Marketplace with Differentially Private Federated Learning under Price Competition},
  journal = {Proceedings of the ACM on Management of Data},
  year = {2024},
  volume = {2},
  number = {4},
  pages = {1--27},
  doi = {10.1145/3677127}
}
Kostenlos starten →