PuSH - Publication Server of Helmholtz Zentrum München

Export: TXT Text RIS Endnote (RIS) BIB BibTeX
Sharma, M.* ; Rainforth, T.* ; Teh, Y.W.* ; Fortuin, V.

Incorporating unlabelled data into bayesian neural networks.

Trans. Machine Learn. Res. 2024, accepted (2024)
Publ. Version/Full Text
Closed
Conventional Bayesian Neural Networks (BNNs) are unable to leverage unlabelled data to improve their predictions. To overcome this limitation, we introduce Self-Supervised Bayesian Neural Networks, which use unlabelled data to learn models with suitable prior predictive distributions. This is achieved by leveraging contrastive pretraining techniques and optimising a variational lower bound. We then show that the prior predictive distributions of self-supervised BNNs capture problem semantics better than conventional BNN priors. In turn, our approach offers improved predictive performance over conventional BNNs, especially in low-budget regimes.
Impact Factor
Scopus SNIP
0.000
0.000
Tags
Annotations
Special Publikation
Hide on homepage

Edit extra information
Edit own tags
Private
Edit own annotation
Private
Hide on publication lists
on hompage
Mark as special
publikation
Publication type Article: Journal article
Document type Review
Language english
Publication Year 2024
HGF-reported in Year 2025
ISSN (print) / ISBN 2835-8856
e-ISSN 2835-8856
Journal Transactions on Machine Learning Research
Quellenangaben Volume: 2024 Issue: , Pages: , Article Number: , Supplement: ,
Publisher Journal of Machine Learning Research Inc.
Reviewing status Peer reviewed
Institute(s) Helmholtz Artifical Intelligence Cooperation Unit (HAICU)
POF-Topic(s) 30205 - Bioengineering and Digital Health
Research field(s) Enabling and Novel Technologies
PSP Element(s) G-530015-001
Scopus ID 85219570717
Erfassungsdatum 2025-05-10
[➜Report correction]