@inproceedings{97163b6493134e6fa23efd47b2561fc1,
title = "Bayesian Variational Federated Learning and Unlearning in Decentralized Networks",
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.",
keywords = "Bayesian learning, Exponential family, Federated learning, Unlearning, Variational inference",
author = "Jinu Gong and Osvaldo Simeone and Joonhyuk Kang",
note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 22nd IEEE International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2021 ; Conference date: 27-09-2021 Through 30-09-2021",
year = "2021",
doi = "10.1109/SPAWC51858.2021.9593225",
language = "English (US)",
series = "IEEE Workshop on Signal Processing Advances in Wireless Communications, SPAWC",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "216--220",
booktitle = "2021 IEEE 22nd International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2021",
address = "United States",
}