Bayesian Variational Federated Learning and Unlearning in Decentralized Networks

Jinu Gong, Osvaldo Simeone, Joonhyuk Kang

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

3 Scopus citations

Abstract

Federated Bayesian learning offers a principled framework for the definition of collaborative training algorithms that are able to quantify epistemic uncertainty and to produce trustworthy decisions. Upon the completion of collaborative training, an agent may decide to exercise her legal "right to be forgotten", which calls for her contribution to the jointly trained model to be deleted and discarded. This paper studies federated learning and unlearning in a decentralized network within a Bayesian framework. It specifically develops federated variational inference (VI) solutions based on the decentralized solution of local free energy minimization problems within exponential-family models and on local gossip-driven communication. The proposed protocols are demonstrated to yield efficient unlearning mechanisms.

Original languageEnglish (US)
Title of host publication2021 IEEE 22nd International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages216-220
Number of pages5
ISBN (Electronic)9781665428514
DOIs
StatePublished - 2021
Event22nd IEEE International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2021 - Lucca, Italy
Duration: Sep 27 2021Sep 30 2021

Publication series

NameIEEE Workshop on Signal Processing Advances in Wireless Communications, SPAWC
Volume2021-September

Conference

Conference22nd IEEE International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2021
Country/TerritoryItaly
CityLucca
Period9/27/219/30/21

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering
  • Computer Science Applications
  • Information Systems

Keywords

  • Bayesian learning
  • Exponential family
  • Federated learning
  • Unlearning
  • Variational inference

Fingerprint

Dive into the research topics of 'Bayesian Variational Federated Learning and Unlearning in Decentralized Networks'. Together they form a unique fingerprint.

Cite this