Comments on "Federated Learning with Differential Privacy: Algorithms and Performance Analysis"

Mahtab Talaei; Iman Izadi

Comments on "Federated Learning with Differential Privacy: Algorithms and Performance Analysis"

Distributed, Parallel, and Cluster Computing 2024-06-11 v1 Cryptography and Security Performance

Authors: Mahtab Talaei , Iman Izadi

Abstract

In the paper by Wei et al. ("Federated Learning with Differential Privacy: Algorithms and Performance Analysis"), the convergence performance of the proposed differential privacy algorithm in federated learning (FL), known as Noising before Model Aggregation FL (NbAFL), was studied. However, the presented convergence upper bound of NbAFL (Theorem 2) is incorrect. This comment aims to present the correct form of the convergence upper bound for NbAFL.

Keywords

federated learning differential privacy

Cite

@article{arxiv.2406.05858,
  title  = {Comments on "Federated Learning with Differential Privacy: Algorithms and Performance Analysis"},
  author = {Mahtab Talaei and Iman Izadi},
  journal= {arXiv preprint arXiv:2406.05858},
  year   = {2024}
}

Related papers

View all related →