Two for the price of one

communication efficient and privacy-preserving distributed average consensus using quantization

Conference Paper (2022)
Author(s)

Qiongxiu Li (Aalborg University)

Milan Lopuhaä-Zwakenberg (University of Twente)

R Heusdens (TU Delft - Signal Processing Systems)

Mads Græsbøll Christensen (Aalborg University)

Research Group
Signal Processing Systems
Copyright
© 2022 Qiongxiu Li, Milan Lopuhaä-Zwakenberg, R. Heusdens, Mads Græsbøll Christensen
More Info
expand_more
Publication Year
2022
Language
English
Copyright
© 2022 Qiongxiu Li, Milan Lopuhaä-Zwakenberg, R. Heusdens, Mads Græsbøll Christensen
Research Group
Signal Processing Systems
Pages (from-to)
2166-2170
ISBN (electronic)
9789082797091
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

Both communication overhead and privacy are main concerns in designing distributed computing algorithms. It is very challenging to address them simultaneously as encryption methods required for privacy-preservation often incur high communication costs. In this paper, we argue that there is a fundamental link between communication efficiency and privacy-preservation through quantization. Based on the observation that quantization, which can save communication bandwidth, will introduce error into the system, we propose a novel privacy-preserving distributed average consensus algorithm which uses the error introduced by quantization as noise to obfuscate the private data for protecting it from being revealed to others. Similar to existing differential privacy based approaches, the proposed approach is robust and has low computational complexity in dealing with two widely considered adversary models: the passive and eavesdropping adversaries. In addition, the method is generally applicable to many distributed optimizers, like PDMM and (generalized) ADMM. We conduct numerical simulations to validate that the proposed approach has superior performance compared to existing algorithms in terms of accuracy, communication bandwidth and privacy.

Files

Two_for_the_price_of_one_commu... (pdf)
(pdf | 0.516 Mb)
- Embargo expired in 01-07-2022
License info not available