PuSH - Publication Server of Helmholtz Zentrum München

Rodemann, J.* ; Goschenhofer, J.* ; Dorigatti, E. ; Nagler, T.* ; Augustin, T.*

Approximately Bayes-Optimal Pseudo-Label Selection.

In: (Proceedings of Machine Learning Research). 2023. 1762-1773 (Proceedings of Machine Learning Research ; 216)
Semi-supervised learning by self-training heavily relies on pseudo-label selection (PLS). This selection often depends on the initial model fit on labeled data. Early overfitting might thus be propagated to the final model by selecting instances with overconfident but erroneous predictions, often referred to as confirmation bias. This paper introduces BPLS, a Bayesian framework for PLS that aims to mitigate this issue. At its core lies a criterion for selecting instances to label: an analytical approximation of the posterior predictive of pseudo-samples. We derive this selection criterion by proving Bayes-optimality of the posterior predictive of pseudo-samples. We further overcome computational hurdles by approximating the criterion analytically. Its relation to the marginal likelihood allows us to come up with an approximation based on Laplace's method and the Gaussian integral. We empirically assess BPLS on simulated and real-world data. When faced with high-dimensional data prone to overfitting, BPLS outperforms traditional PLS methods.
Additional Metrics?
[➜Log in]
Edit extra informations Login
Publication type Article: Conference contribution
Corresponding Author
Conference Title Proceedings of Machine Learning Research
Quellenangaben Volume: 216, Issue: , Pages: 1762-1773 Article Number: , Supplement: ,
Non-patent literature Publications
Institute(s) Institute of Computational Biology (ICB)