Collaborative Mean Estimation over Intermittently Connected Networks with Peer-To-Peer Privacy

Rajarshi Saha; Mohamed Seif; Michal Yemini; Andrea J. Goldsmith; H. Vincent Poor

doi:10.1109/ISIT54713.2023.10206910

Collaborative Mean Estimation over Intermittently Connected Networks with Peer-To-Peer Privacy

Rajarshi Saha, Mohamed Seif, Michal Yemini, Andrea J. Goldsmith, H. Vincent Poor

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

This work considers the problem of Distributed Mean Estimation (DME) over networks with intermittent connectivity, where the goal is to learn a global statistic over the data samples localized across distributed nodes with the help of a central server. To mitigate the impact of intermittent links, nodes can collaborate with their neighbors to compute local consensus which they forward to the central server. In such a setup, the communications between any pair of nodes must satisfy local differential privacy constraints. We study the tradeoff between collaborative relaying and privacy leakage due to the additional data sharing among nodes and, subsequently, propose a novel differentially private collaborative algorithm for DME to achieve the optimal tradeoff. Finally, we present numerical simulations to substantiate our theoretical findings.

Original language	English
Title of host publication	2023 IEEE International Symposium on Information Theory, ISIT 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	174-179
Number of pages	6
ISBN (Electronic)	9781665475549
DOIs	https://doi.org/10.1109/ISIT54713.2023.10206910
State	Published - 2023
Event	2023 IEEE International Symposium on Information Theory, ISIT 2023 - Taipei, Taiwan, Province of China Duration: 25 Jun 2023 → 30 Jun 2023

Publication series

Name	IEEE International Symposium on Information Theory - Proceedings
Volume	2023-June
ISSN (Print)	2157-8095

Conference

Conference	2023 IEEE International Symposium on Information Theory, ISIT 2023
Country/Territory	Taiwan, Province of China
City	Taipei
Period	25/06/23 → 30/06/23

Bibliographical note

Publisher Copyright:
© 2023 IEEE.

Funding

This work was supported by the AFOSR award #002484665, a Huawei Intelligent Spectrum grant, and NSF grants CCF-1908308 & CNS-2128448.

Funders	Funder number
Huawei Intelligent Spectrum
National Science Foundation	CNS-2128448, CCF-1908308
Air Force Office of Scientific Research	002484665

Access to Document

10.1109/ISIT54713.2023.10206910

Cite this

Saha, R., Seif, M., Yemini, M., Goldsmith, A. J., & Vincent Poor, H. (2023). Collaborative Mean Estimation over Intermittently Connected Networks with Peer-To-Peer Privacy. In 2023 IEEE International Symposium on Information Theory, ISIT 2023 (pp. 174-179). (IEEE International Symposium on Information Theory - Proceedings; Vol. 2023-June). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISIT54713.2023.10206910

@inproceedings{f2cd65f020ba47ebabe69c0e4f2e5559,

title = "Collaborative Mean Estimation over Intermittently Connected Networks with Peer-To-Peer Privacy",

abstract = "This work considers the problem of Distributed Mean Estimation (DME) over networks with intermittent connectivity, where the goal is to learn a global statistic over the data samples localized across distributed nodes with the help of a central server. To mitigate the impact of intermittent links, nodes can collaborate with their neighbors to compute local consensus which they forward to the central server. In such a setup, the communications between any pair of nodes must satisfy local differential privacy constraints. We study the tradeoff between collaborative relaying and privacy leakage due to the additional data sharing among nodes and, subsequently, propose a novel differentially private collaborative algorithm for DME to achieve the optimal tradeoff. Finally, we present numerical simulations to substantiate our theoretical findings.",

author = "Rajarshi Saha and Mohamed Seif and Michal Yemini and Goldsmith, {Andrea J.} and {Vincent Poor}, H.",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 IEEE International Symposium on Information Theory, ISIT 2023 ; Conference date: 25-06-2023 Through 30-06-2023",

year = "2023",

doi = "10.1109/ISIT54713.2023.10206910",

language = "אנגלית",

series = "IEEE International Symposium on Information Theory - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "174--179",

booktitle = "2023 IEEE International Symposium on Information Theory, ISIT 2023",

address = "ארצות הברית",

}

Saha, R, Seif, M, Yemini, M, Goldsmith, AJ & Vincent Poor, H 2023, Collaborative Mean Estimation over Intermittently Connected Networks with Peer-To-Peer Privacy. in 2023 IEEE International Symposium on Information Theory, ISIT 2023. IEEE International Symposium on Information Theory - Proceedings, vol. 2023-June, Institute of Electrical and Electronics Engineers Inc., pp. 174-179, 2023 IEEE International Symposium on Information Theory, ISIT 2023, Taipei, Taiwan, Province of China, 25/06/23. https://doi.org/10.1109/ISIT54713.2023.10206910

Collaborative Mean Estimation over Intermittently Connected Networks with Peer-To-Peer Privacy. / Saha, Rajarshi; Seif, Mohamed; Yemini, Michal et al.
2023 IEEE International Symposium on Information Theory, ISIT 2023. Institute of Electrical and Electronics Engineers Inc., 2023. p. 174-179 (IEEE International Symposium on Information Theory - Proceedings; Vol. 2023-June).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Collaborative Mean Estimation over Intermittently Connected Networks with Peer-To-Peer Privacy

AU - Saha, Rajarshi

AU - Seif, Mohamed

AU - Yemini, Michal

AU - Goldsmith, Andrea J.

AU - Vincent Poor, H.

PY - 2023

Y1 - 2023

N2 - This work considers the problem of Distributed Mean Estimation (DME) over networks with intermittent connectivity, where the goal is to learn a global statistic over the data samples localized across distributed nodes with the help of a central server. To mitigate the impact of intermittent links, nodes can collaborate with their neighbors to compute local consensus which they forward to the central server. In such a setup, the communications between any pair of nodes must satisfy local differential privacy constraints. We study the tradeoff between collaborative relaying and privacy leakage due to the additional data sharing among nodes and, subsequently, propose a novel differentially private collaborative algorithm for DME to achieve the optimal tradeoff. Finally, we present numerical simulations to substantiate our theoretical findings.

AB - This work considers the problem of Distributed Mean Estimation (DME) over networks with intermittent connectivity, where the goal is to learn a global statistic over the data samples localized across distributed nodes with the help of a central server. To mitigate the impact of intermittent links, nodes can collaborate with their neighbors to compute local consensus which they forward to the central server. In such a setup, the communications between any pair of nodes must satisfy local differential privacy constraints. We study the tradeoff between collaborative relaying and privacy leakage due to the additional data sharing among nodes and, subsequently, propose a novel differentially private collaborative algorithm for DME to achieve the optimal tradeoff. Finally, we present numerical simulations to substantiate our theoretical findings.

UR - http://www.scopus.com/inward/record.url?scp=85171440493&partnerID=8YFLogxK

U2 - 10.1109/ISIT54713.2023.10206910

DO - 10.1109/ISIT54713.2023.10206910

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:85171440493

T3 - IEEE International Symposium on Information Theory - Proceedings

SP - 174

EP - 179

BT - 2023 IEEE International Symposium on Information Theory, ISIT 2023

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2023 IEEE International Symposium on Information Theory, ISIT 2023

Y2 - 25 June 2023 through 30 June 2023

ER -

Saha R, Seif M, Yemini M, Goldsmith AJ, Vincent Poor H. Collaborative Mean Estimation over Intermittently Connected Networks with Peer-To-Peer Privacy. In 2023 IEEE International Symposium on Information Theory, ISIT 2023. Institute of Electrical and Electronics Engineers Inc. 2023. p. 174-179. (IEEE International Symposium on Information Theory - Proceedings). doi: 10.1109/ISIT54713.2023.10206910

Collaborative Mean Estimation over Intermittently Connected Networks with Peer-To-Peer Privacy

Abstract

Publication series

Conference

Bibliographical note

Funding

Access to Document

Other files and links

Fingerprint

Cite this