ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2212.09704
10
5

Rate-Privacy-Storage Tradeoff in Federated Learning with Top rrr Sparsification

19 December 2022
Sajani Vithana
S. Ulukus
    FedML
ArXivPDFHTML
Abstract

We investigate the trade-off between rate, privacy and storage in federated learning (FL) with top rrr sparsification, where the users and the servers in the FL system only share the most significant rrr and r′r'r′ fractions, respectively, of updates and parameters in the FL process, to reduce the communication cost. We present schemes that guarantee information theoretic privacy of the values and indices of the sparse updates sent by the users at the expense of a larger storage cost. To this end, we generalize the scheme to reduce the storage cost by allowing a certain amount of information leakage. Thus, we provide the general trade-off between the communication cost, storage cost, and information leakage in private FL with top rrr sparsification, along the lines of two proposed schemes.

View on arXiv
Comments on this paper