Communication-Efficient and Privacy-Aware Distributed Learning
Loading...
Access rights
openAccess
URL
Journal Title
Journal ISSN
Volume Title
A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä
This publication is imported from Aalto University research portal.
View publication in the Research portal (opens in new window)
View/Open full text file from the Research portal (opens in new window)
Other link related to publication (opens in new window)
View publication in the Research portal (opens in new window)
View/Open full text file from the Research portal (opens in new window)
Other link related to publication (opens in new window)
Date
2023
Major/Subject
Mcode
Degree programme
Language
en
Pages
16
705-720
705-720
Series
IEEE Transactions on Signal and Information Processing over Networks, Volume 9
Abstract
Communication efficiency and privacy are two key concerns in modern distributed computing systems. Towards this goal, this article proposes partial sharing private distributed learning (PPDL) algorithms that offer communication efficiency while preserving privacy, thus making them suitable for applications with limited resources in adversarial environments. First, we propose a noise injection-based PPDL algorithm that achieves communication efficiency by sharing only a fraction of the information at each consensus iteration and provides privacy by perturbing the information exchanged among neighbors. To further increase privacy, local information is randomly decomposed into private and public substates before sharing with the neighbors. This results in a decomposition-and noise-injection-based PPDL strategy in which only a freaction of the perturbeesd public substate is shared during local collaborations, whereas the private substate is updated locally without being shared. To determine the impact of communication savings and privacy preservation on the performance of distributed learning algorithms, we analyze the mean and mean-square convergence of the proposed algorithms. Moreover, we investigate the privacy of agents by characterizing privacy as the mean squared error of the estimate of private information at the honest-but-curious adversary. The analytical results show a tradeoff between communication efficiency and privacy in proposed PPDL algorithms, while decomposition-and noise-injection-based PPDL improves privacy compared to noise-injection-based PPDL. Lastly, numerical simulations corroborate the analytical findings.Description
Publisher Copyright: © 2015 IEEE.
Keywords
Average consensus, communication efficiency, distributed learning, multiagent systems, privacy-preservation
Other note
Citation
Gogineni, V C, Moradi, A, Venkategowda, N K D & Werner, S 2023, ' Communication-Efficient and Privacy-Aware Distributed Learning ', IEEE Transactions on Signal and Information Processing over Networks, vol. 9, pp. 705-720 . https://doi.org/10.1109/TSIPN.2023.3322783