Home
Deutsch
Advanced Search
Browse by ...
Publication overview
Contact persons
Help
Postprint
 |
|
as soon as is submitted to ZB.
Incorporating unlabelled data into bayesian neural networks.
Trans. Machine Learn. Res. 2024, accepted (2024)
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.
Additional Metrics?
Edit extra informations
Login
Publication type
Article: Journal article
Document type
Review
ISSN (print) / ISBN
2835-8856
e-ISSN
2835-8856
Quellenangaben
Volume: 2024
Publisher
Journal of Machine Learning Research Inc.
Non-patent literature
Publications
Reviewing status
Peer reviewed