An Unequal Error Protection-based Coded Transmission for Federated Learning

Qingya Lu, Rongchi Xu, Chang Liu, Shuangyang Li, Baoming Bai

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

1 Citation (Scopus)

Abstract

Effective data transmission plays a crucial role in federated learning (FL), which enables collaborative model training without centralizing data. This paper proposes a new coded transmission to enhance the communication quality for FL. The proposed coded transmission incorporates weight quantization, multilevel coding, set partitioning, and multi-stage decoding which are optimized to improve the FL performance. Furthermore, the unequal error protection (UEP) strategy is adopted in the proposed coded transmission, which allows the code rates to be optimized according to the significance of the quantized data. Simulation results demonstrate that the proposed UEP-based coded transmission outperforms conventional bit-interleaved coded modulation (BICM) scheme in terms of NMSE performance for FL, which, in return, improves the FL performance.

Original languageEnglish
Title of host publication2023 IEEE/CIC International Conference on Communications in China, ICCC Workshops 2023
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages11-5
Number of pages5
ISBN (Electronic)9798350345407
DOIs
Publication statusPublished - Aug 2023
Event2023 IEEE/CIC International Conference on Communications in China, ICCC Workshops 2023 - Dalian, China
Duration: 10 Aug 202312 Aug 2023

Publication series

Name2023 IEEE/CIC International Conference on Communications in China, ICCC Workshops 2023

Conference

Conference2023 IEEE/CIC International Conference on Communications in China, ICCC Workshops 2023
Country/TerritoryChina
CityDalian
Period10/08/2312/08/23

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Signal Processing

Fingerprint

Dive into the research topics of 'An Unequal Error Protection-based Coded Transmission for Federated Learning'. Together they form a unique fingerprint.

Cite this