paper-with-me

홈 › Papers

Differentially Private Federated Learning via Inexact ADMM with Multiple Local Updates

2022-02-18 · Minseok Ryu, Kibaek Kim

Differential privacy (DP) techniques can be applied to the federated learning model to statistically guarantee data privacy against inference attacks to communication among the learning agents. While ensuring strong data privacy, however, the DP techniques hinder achieving a greater learning performance. In this paper we develop a DP inexact alternating direction method of multipliers algorithm with multiple local updates for federated learning, where a sequence of convex subproblems is solved with the objective perturbation by random noises generated from a Laplace distribution. We show that our algorithm provides $\bar{\epsilon}$-DP for every iteration, where $\bar{\epsilon}$ is a privacy budget controlled by the user. We also present convergence analyses of the proposed algorithm. Using MNIST and FEMNIST datasets for the image classification, we demonstrate that our algorithm reduces the testing error by at most $31\%$ compared with the existing DP algorithm, while achieving the same level of data privacy. The numerical experiment also shows that our algorithm converges faster than the existing algorithm.

📄 PDF Abstract BibTeX arXiv:2202.09409

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learningimage-classificationImage Classification

Similar Papers 제목 키워드 기반

Differentially Private Federated Learning via Inexact ADMM

2021-06-11 · Minseok Ryu, Kibaek Kim

Differential privacy (DP) techniques can be applied to the federated learning model to protect data privacy against inference attacks to communication among the learning agents. The DP techniques, however, hinder achievi…

Federated Learningimage-classificationImage Classification

Differentially Private ADMM for Distributed Medical Machine Learning

2019-01-07 · Jiahao Ding, Xiaoqi Qin, Wenjun Xu, Yanmin Gong 외

Due to massive amounts of data distributed across multiple locations, distributed machine learning has attracted a lot of research interests. Alternating Direction Method of Multipliers (ADMM) is a powerful method of des…

BIG-bench Machine Learning

From Noisy Fixed-Point Iterations to Private ADMM for Centralized and Federated Learning

2023-02-24 · Edwige Cyffers, Aurélien Bellet, Debabrota Basu

We study differentially private (DP) machine learning algorithms as instances of noisy fixed-point iterations, in order to derive privacy and utility results from this well-studied framework. We show that this new perspe…

Federated Learning

Differentially Private ADMM for Convex Distributed Learning: Improved Accuracy via Multi-Step Approximation

2020-05-16 · Zonghao Huang, Yanmin Gong

Alternating Direction Method of Multipliers (ADMM) is a popular algorithm for distributed learning, where a network of nodes collaboratively solve a regularized empirical risk minimization by iterative local computation …

FedADMM-InSa: An Inexact and Self-Adaptive ADMM for Federated Learning

2024-02-21 · Yongcun Song, Ziqi Wang, Enrique Zuazua

Federated learning (FL) is a promising framework for learning from distributed data while maintaining privacy. The development of efficient FL algorithms encounters various challenges, including heterogeneous data and sy…

Federated Learning