Privacy-Enhanced Federated Learning for Non-IID Data

Qingjie Tan, Shuhui Wu () and Yuanhong Tao
Additional contact information
Qingjie Tan: School of Science, Zhejiang University of Science and Technology, Hangzhou 310023, China
Shuhui Wu: School of Science, Zhejiang University of Science and Technology, Hangzhou 310023, China
Yuanhong Tao: School of Science, Zhejiang University of Science and Technology, Hangzhou 310023, China

Mathematics, 2023, vol. 11, issue 19, 1-21

Abstract: Federated learning (FL) allows the collaborative training of a collective model by a vast number of decentralized clients while ensuring that these clients’ data remain private and are not shared. In practical situations, the training data utilized in FL often exhibit non-IID characteristics, hence diminishing the efficacy of FL. Our study presents a novel privacy-preserving FL algorithm, HW-DPFL, which leverages data label distribution similarity as a basis for its design. Our proposed approach achieves this objective without incurring any additional overhead communication. In this study, we provide evidence to support the assertion that our approach improves the privacy guarantee and convergence of FL both theoretically and empirically.

Keywords: federated learning; Hellinger distance; differential privacy; non-IID data (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/2227-7390/11/19/4123/pdf (application/pdf)
https://www.mdpi.com/2227-7390/11/19/4123/ (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:19:p:4123-:d:1250906

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 ().