Tackling covariate shift with node-based Bayesian neural networks
Loading...
Access rights
openAccess
publishedVersion
URL
Journal Title
Journal ISSN
Volume Title
A4 Artikkeli konferenssijulkaisussa
This publication is imported from Aalto University research portal.
View publication in the Research portal (opens in new window)
View/Open full text file from the Research portal (opens in new window)
Other link related to publication (opens in new window)
View publication in the Research portal (opens in new window)
View/Open full text file from the Research portal (opens in new window)
Other link related to publication (opens in new window)
Date
Department
Major/Subject
Mcode
Degree programme
Language
en
Pages
25
Series
Proceedings of the 39th International Conference on Machine Learning, pp. 21751-21775, Proceedings of Machine Learning Research ; Volume 162
Abstract
Bayesian neural networks (BNNs) promise improved generalization under covariate shift by providing principled probabilistic representations of epistemic uncertainty. However, weight-based BNNs often struggle with high computational complexity of large-scale architectures and datasets. Node-based BNNs have recently been introduced as scalable alternatives, which induce epistemic uncertainty by multiplying each hidden node with latent random variables, while learning a point-estimate of the weights. In this paper, we interpret these latent noise variables as implicit representations of simple and domain-agnostic data perturbations during training, producing BNNs that perform well under covariate shift due to input corruptions. We observe that the diversity of the implicit corruptions depends on the entropy of the latent variables, and propose a straightforward approach to increase the entropy of these variables during training. We evaluate the method on out-of-distribution image classification benchmarks, and show improved uncertainty estimation of node-based BNNs under covariate shift due to input perturbations. As a side effect, the method also provides robustness against noisy training labels.Description
Keywords
Other note
Citation
Trinh, T Q, Heinonen, M, Acerbi, L & Kaski, S 2022, Tackling covariate shift with node-based Bayesian neural networks. in K Chaudhuri, S Jegelka, L Song, C Szepesvari, G Niu & S Sabato (eds), Proceedings of the 39th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 162, JMLR, pp. 21751-21775, International Conference on Machine Learning, Baltimore, Maryland, United States, 17/07/2022. < https://proceedings.mlr.press/v162/trinh22a.html >