Efficient Model Quality Evaluation in Federated Learning via Functional Encryption

Ruichen Xu, Yang He, Yi Wu*, Chenfei Hu, Zijie Pan, Liehuang Zhu, Chuan Zhang

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Federated Learning(FL) is a distributed machine learning paradigm that exchanges data among multiple parties without directly sharing the original data. However, FL faces the inherent issue of statistical heterogeneity. Recently, some privacy preserving federated learning scheme have considered this issue. But they use homomorphic encryption, which imposes significant computational and communication overhead on the clients. To address this issue, we propose an efficient model quality evaluation scheme in FL via functional encryption. Specifically, we first use inner product functional encryption(IPFE) to efficiently and securely calculate the cosine similarity between global update and each local update on the server, then use clustering algorithm to assign weights to each client based on cosine similarity, and finally update the global model through weighted aggregation. Experimental results show that compared with other model quality evaluation scheme, our approach increases the computational efficiency by up to 25% and reduces communication cost by up to 70%.

Original languageEnglish
Title of host publicationProceedings - 2024 Cross Strait Radio Science and Wireless Technology Conference, CSRSWTC 2024
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9798331507794
DOIs
Publication statusPublished - 2024
Event2024 Cross Strait Radio Science and Wireless Technology Conference, CSRSWTC 2024 - Macao, China
Duration: 4 Nov 20247 Nov 2024

Publication series

NameProceedings - 2024 Cross Strait Radio Science and Wireless Technology Conference, CSRSWTC 2024

Conference

Conference2024 Cross Strait Radio Science and Wireless Technology Conference, CSRSWTC 2024
Country/TerritoryChina
CityMacao
Period4/11/247/11/24

Keywords

  • Federated Learning
  • Functional Encryption
  • Model Quality Evaluation
  • Privacy-Preserving

Fingerprint

Dive into the research topics of 'Efficient Model Quality Evaluation in Federated Learning via Functional Encryption'. Together they form a unique fingerprint.

Cite this