CoBAAF: Controlled Bayesian Air Aggregation Federated Learning from Heterogeneous Data

Tomer Gafni, Kobi Cohen, Yonina C. Eldar

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

Abstract

Federated learning (FL) is an emerging machine learning paradigm for training models across multiple edge devices holding local data sets, without explicitly exchanging the data. A major challenge in FL is to reduce the bandwidth and energy consumption due to the repeated transmissions of large volumes of data by a large number of users over the wireless channel, and to handle statistical heterogeneity of users data. In this paper we present a novel algorithm, dubbed Controlled Bayesian Air Aggregation Federated-learning (CoBAAF), that handles statistical heterogeneity in noisy networks using a joint design of three main steps in FL: Model distribution, local training, and global aggregation. Specifically, CoBAAF controls the drift in local updates using a correction term, and allows users to transmit their data signal simultaneously over MAC. Second, it adopts a Bayesian approach to average properly the channel output, thus mitigating the effect of the noise and fading induced by the channel. We analyze the convergence of CoBAAF to the loss minimizing model theoretically, showing its ability to achieve a convergence rate similar to that achieved over error-free channels. Extensive simulation results demonstrate the improved convergence of CoBAAF for training in machine learning problems.

Original languageEnglish
Title of host publication2022 58th Annual Allerton Conference on Communication, Control, and Computing, Allerton 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9798350399981
DOIs
StatePublished - 1 Jan 2022
Event58th Annual Allerton Conference on Communication, Control, and Computing, Allerton 2022 - Monticello, United States
Duration: 27 Sep 202230 Sep 2022

Publication series

Name2022 58th Annual Allerton Conference on Communication, Control, and Computing, Allerton 2022

Conference

Conference58th Annual Allerton Conference on Communication, Control, and Computing, Allerton 2022
Country/TerritoryUnited States
CityMonticello
Period27/09/2230/09/22

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Computer Science Applications
  • Computer Vision and Pattern Recognition
  • Signal Processing
  • Control and Optimization

Fingerprint

Dive into the research topics of 'CoBAAF: Controlled Bayesian Air Aggregation Federated Learning from Heterogeneous Data'. Together they form a unique fingerprint.

Cite this