Show simple item record

dc.contributor.authorGogineni, Vinay Chakravarthi
dc.contributor.authorMoradi, Ashkan
dc.contributor.authorDasanadoddi Venkategowda, Naveen Kumar
dc.contributor.authorWerner, Anders Stefan
dc.date.accessioned2023-10-30T08:45:11Z
dc.date.available2023-10-30T08:45:11Z
dc.date.created2023-10-27T09:58:41Z
dc.date.issued2023
dc.identifier.issn2373-7778
dc.identifier.urihttps://hdl.handle.net/11250/3099310
dc.description.abstractCommunication 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.en_US
dc.language.isoengen_US
dc.publisherIEEEen_US
dc.rightsNavngivelse 4.0 Internasjonal*
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/deed.no*
dc.titleCommunication-efficient and privacy-aware distributed learningen_US
dc.title.alternativeCommunication-efficient and privacy-aware distributed learningen_US
dc.typePeer revieweden_US
dc.typeJournal articleen_US
dc.description.versionacceptedVersionen_US
dc.rights.holderCopyright © 2023 IEEEen_US
dc.source.journalIEEE Transactions on Signal and Information Processing over Networksen_US
dc.identifier.doi10.1109/TSIPN.2023.3322783
dc.identifier.cristin2189063
cristin.ispublishedtrue
cristin.fulltextpostprint
cristin.qualitycode2


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

Navngivelse 4.0 Internasjonal
Except where otherwise noted, this item's license is described as Navngivelse 4.0 Internasjonal