Wireless Federated Distillation for Distributed Edge Learning with Heterogeneous Data

Jin Hyun Ahn, Osvaldo Simeone, Joonhyuk Kang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

72 Scopus citations

Abstract

Cooperative training methods for distributed machine learning typically assume noiseless and ideal communication channels. This work studies some of the opportunities and challenges arising from the presence of wireless communication links. We specifically consider wireless implementations of Federated Learning (FL) and Federated Distillation (FD), as well as of a novel Hybrid Federated Distillation (HFD) scheme. Both digital implementations based on separate source-channel coding and over-the-air computing implementations based on joint source-channel coding are proposed and evaluated over Gaussian multiple-access channels.

Original languageEnglish (US)
Title of host publication2019 IEEE 30th Annual International Symposium on Personal, Indoor and Mobile Radio Communications, PIMRC 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781538681107
DOIs
StatePublished - Sep 2019
Event30th IEEE Annual International Symposium on Personal, Indoor and Mobile Radio Communications, PIMRC 2019 - Istanbul, Turkey
Duration: Sep 8 2019Sep 11 2019

Publication series

NameIEEE International Symposium on Personal, Indoor and Mobile Radio Communications, PIMRC
Volume2019-September

Conference

Conference30th IEEE Annual International Symposium on Personal, Indoor and Mobile Radio Communications, PIMRC 2019
Country/TerritoryTurkey
CityIstanbul
Period9/8/199/11/19

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Wireless Federated Distillation for Distributed Edge Learning with Heterogeneous Data'. Together they form a unique fingerprint.

Cite this