EUVIMEDEUVIMED entdecken
Crossref

A Socially Optimal Data Marketplace With Differentially Private Federated Learning

Peng Sun, Guocheng Liao, Xu Chen, Jianwei Huang

IEEE/ACM Transactions on Networking · 2024-06 · 32 (3) · 2221-2236

DOI: 10.1109/tnet.2024.3351864 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE/ACM Transactions on Networking, 2024-06. Verfasst von Peng Sun und 3 weiteren Autor:innen. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 53 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Shenzhen Science and Technology Innovation Program, Basic and Applied Basic Research Foundation of Guangdong Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Federated learning (FL) enables multiple data owners to collaboratively train machine learning (ML) models for different model requesters while keeping data localized. Thus, FL can mitigate privacy leakage in conventional data marketplaces for ML applications requiring raw data trading for centralized model training. Nevertheless, data owners involved in FL may still suffer potential privacy leakage from gradient exposure to the model requesters. In this work, we advocate a novel data marketplace with differentially private federated learning (DPFL) to reduce such threats and maximize the social welfare. Designing such a marketplace involves several challenges. First, it is difficult to determine the privacy budget that a data owner should choose for a model requester, since they have conflicting objectives and private utility/cost information. Second, each data owner sustains privacy costs from his friends’ participation in DPFL due to data correlations, which introduces a negative externality to the market. We design a social-aware iterative double auction (SARDA) mechanism to resolve these challenges and achieve socially optimal market operation. SARDA employs a broker to coordinate the interactions between data owners and model requesters and induces them to truthfully report by iteratively updating the allocation and pricing rules. Moreover, SARDA accounts for the negative externality by incorporating others’ bids to reimburse each data owner. We show that SARDA achieves the optimal social performance and creates up to 60% higher social welfare than the social-agnostic benchmark.

Förderung

  • National Natural Science Foundation of China
  • Shenzhen Science and Technology Innovation Program
  • Basic and Applied Basic Research Foundation of Guangdong Province
  • Shenzhen Key Laboratory of Crowd Intelligence Empowered Low-Carbon Energy Network
  • Shenzhen Institute of Artificial Intelligence and Robotics for Society
  • Natural Science Foundation of Hunan Province

Zitieren

APA

Sun, P., Liao, G., Chen, X., & Huang, J. (2024). A Socially Optimal Data Marketplace With Differentially Private Federated Learning. IEEE/ACM Transactions on Networking, 32(3), 2221-2236. https://doi.org/10.1109/tnet.2024.3351864

Vancouver

Sun P, Liao G, Chen X, Huang J. A Socially Optimal Data Marketplace With Differentially Private Federated Learning. IEEE/ACM Transactions on Networking. 2024;32(3):2221-2236. doi:10.1109/tnet.2024.3351864

BibTeX
@article{Sun2024,
  author = {Sun, Peng and Liao, Guocheng and Chen, Xu and Huang, Jianwei},
  title = {A Socially Optimal Data Marketplace With Differentially Private Federated Learning},
  journal = {IEEE/ACM Transactions on Networking},
  year = {2024},
  volume = {32},
  number = {3},
  pages = {2221--2236},
  doi = {10.1109/tnet.2024.3351864}
}
Kostenlos starten →