Privacy-Preserving Distributed Learning via Newton Algorithm

Zilong Cao, Xiao Guo and Hai Zhang ()
Additional contact information
Zilong Cao: School of Mathematics, Northwest University, Xi’an 710127, China
Xiao Guo: School of Mathematics, Northwest University, Xi’an 710127, China
Hai Zhang: School of Mathematics, Northwest University, Xi’an 710127, China

Mathematics, 2023, vol. 11, issue 18, 1-21

Abstract: Federated learning (FL) is a prominent distributed learning framework. The main barriers of FL include communication cost and privacy breaches. In this work, we propose a novel privacy-preserving second-order-based FL method, called GDP-LocalNewton . To improve the communication efficiency, we use Newton’s method to iterate and allow local computations before aggregation. To ensure strong privacy guarantee, we make use of the notion of differential privacy (DP) to add Gaussian noise in each iteration. Using advanced tools of Gaussian differential privacy (GDP), we prove that the proposed algorithm satisfies the strong notion of GDP. We also establish the convergence of our algorithm. It turns out that the convergence error comes from the local computation and Gaussian noise for DP. We conduct experiments to show the merits of the proposed algorithm.

Keywords: federated learning; differential privacy; second-order method (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/11/18/3807/pdf (application/pdf)
https://www.mdpi.com/2227-7390/11/18/3807/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:11:y:2023:i:18:p:3807-:d:1233332

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().