Privacy-preserving Decentralized Federated Learning over Time-varying Communication Graph
ACM Transactions on Privacy and Security · 30.08.2023 · 26 (3) · 1-39
DOI: 10.1145/3591354 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Privacy and Security, online erschienen am 26.06.2023. Verfasst von Yang Lu und 2 weiteren Autor:innen. Die Arbeit wurde bisher 33-mal zitiert (Crossref) und nennt 76 Literaturangaben.
Abstract (Originalsprache)
Establishing how a set of learners can provide privacy-preserving federated learning in a fully decentralized (peer-to-peer, no coordinator) manner is an open problem. We propose the first privacy-preserving consensus-based algorithm for the distributed learners to achieve decentralized global model aggregation in an environment of high mobility, where participating learners and the communication graph between them may vary during the learning process. In particular, whenever the communication graph changes, the Metropolis-Hastings method [ 69 ] is applied to update the weighted adjacency matrix based on the current communication topology. In addition, the Shamir’s secret sharing (SSS) scheme [ 61 ] is integrated to facilitate privacy in reaching consensus of the global model. The article establishes the correctness and privacy properties of the proposed algorithm. The computational efficiency is evaluated by a simulation built on a federated learning framework with a real-world dataset.
Zitieren
APA
Lu, Y., Yu, Z., & Suri, N. (2023). Privacy-preserving Decentralized Federated Learning over Time-varying Communication Graph. ACM Transactions on Privacy and Security, 26(3), 1-39. https://doi.org/10.1145/3591354
Vancouver
Lu Y, Yu Z, Suri N. Privacy-preserving Decentralized Federated Learning over Time-varying Communication Graph. ACM Transactions on Privacy and Security. 2023;26(3):1-39. doi:10.1145/3591354
BibTeX
@article{Lu2023,
author = {Lu, Yang and Yu, Zhengxin and Suri, Neeraj},
title = {Privacy-preserving Decentralized Federated Learning over Time-varying Communication Graph},
journal = {ACM Transactions on Privacy and Security},
year = {2023},
volume = {26},
number = {3},
pages = {1--39},
doi = {10.1145/3591354}
}
EUVIMED