PuSH - Publikationsserver des Helmholtz Zentrums München

Sharma, M.* ; Rainforth, T.* ; Teh, Y.W.* ; Fortuin, V.

Incorporating unlabelled data into bayesian neural networks.

Trans. Machine Learn. Res. 2024, accepted (2024)
Postprint
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.
Weitere Metriken?
[➜Einloggen]
Zusatzinfos bearbeiten [➜Einloggen]
Publikationstyp Artikel: Journalartikel
Dokumenttyp Review
Korrespondenzautor
ISSN (print) / ISBN 2835-8856
e-ISSN 2835-8856
Zeitschrift Transactions on Machine Learning Research
Quellenangaben Band: 2024 Heft: , Seiten: , Artikelnummer: , Supplement: ,
Verlag Journal of Machine Learning Research Inc.
Nichtpatentliteratur Publikationen
Begutachtungsstatus Peer reviewed
Institut(e) Helmholtz Artifical Intelligence Cooperation Unit (HAICU)