DC Field | Value | Language |
---|---|---|
dc.contributor.author | Gong, Jinu | ko |
dc.contributor.author | Simeone, Osvaldo | ko |
dc.contributor.author | Kang, Joonhyuk | ko |
dc.date.accessioned | 2022-08-24T07:00:57Z | - |
dc.date.available | 2022-08-24T07:00:57Z | - |
dc.date.created | 2022-07-29 | - |
dc.date.created | 2022-07-29 | - |
dc.date.issued | 2021-09 | - |
dc.identifier.citation | 2021 IEEE 22nd International Workshop on Signal Processing Advances in Wireless Communications (SPAWC), pp.216 - 220 | - |
dc.identifier.uri | http://hdl.handle.net/10203/298073 | - |
dc.description.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. | - |
dc.language | English | - |
dc.publisher | Institute of Electrical and Electronics Engineers Inc. | - |
dc.title | Bayesian Variational Federated Learning and Unlearning in Decentralized Networks | - |
dc.type | Conference | - |
dc.identifier.wosid | 000783745500044 | - |
dc.identifier.scopusid | 2-s2.0-85119943637 | - |
dc.type.rims | CONF | - |
dc.citation.beginningpage | 216 | - |
dc.citation.endingpage | 220 | - |
dc.citation.publicationname | 2021 IEEE 22nd International Workshop on Signal Processing Advances in Wireless Communications (SPAWC) | - |
dc.identifier.conferencecountry | IT | - |
dc.identifier.conferencelocation | Lucca | - |
dc.identifier.doi | 10.1109/SPAWC51858.2021.9593225 | - |
dc.contributor.localauthor | Kang, Joonhyuk | - |
dc.contributor.nonIdAuthor | Simeone, Osvaldo | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.