Home > Research > Publications & Outputs > Semi-Supervised Learning guided by the Generali...

Electronic data

  • 2405.15294v2

    Final published version, 446 KB, PDF document

    Available under license: CC BY: Creative Commons Attribution 4.0 International License


View graph of relations

Semi-Supervised Learning guided by the Generalized Bayes Rule under Soft Revision

Research output: Working paperPreprint

Publication date24/05/2024
<mark>Original language</mark>English


We provide a theoretical and computational investigation of the Gamma-Maximin method with soft revision, which was recently proposed as a robust criterion for pseudo-label selection (PLS) in semi-supervised learning. Opposed to traditional methods for PLS we use credal sets of priors ("generalized Bayes") to represent the epistemic modeling uncertainty. These latter are then updated by the Gamma-Maximin method with soft revision. We eventually select pseudo-labeled data that are most likely in light of the least favorable distribution from the so updated credal set. We formalize the task of finding optimal pseudo-labeled data w.r.t. the Gamma-Maximin method with soft revision as an optimization problem. A concrete implementation for the class of logistic models then allows us to compare the predictive power of the method with competing approaches. It is observed that the Gamma-Maximin method with soft revision can achieve very promising results, especially when the proportion of labeled data is low.

Bibliographic note

Accepted at the 11th International Conference on Soft Methods in Probability and Statistics (SMPS) 2024