English

In all LikelihoodS: How to Reliably Select Pseudo-Labeled Data for Self-Training in Semi-Supervised Learning

Machine Learning 2023-03-03 v1 Machine Learning Statistics Theory Methodology Statistics Theory

Abstract

Self-training is a simple yet effective method within semi-supervised learning. The idea is to iteratively enhance training data by adding pseudo-labeled data. Its generalization performance heavily depends on the selection of these pseudo-labeled data (PLS). In this paper, we aim at rendering PLS more robust towards the involved modeling assumptions. To this end, we propose to select pseudo-labeled data that maximize a multi-objective utility function. The latter is constructed to account for different sources of uncertainty, three of which we discuss in more detail: model selection, accumulation of errors and covariate shift. In the absence of second-order information on such uncertainties, we furthermore consider the generic approach of the generalized Bayesian alpha-cut updating rule for credal sets. As a practical proof of concept, we spotlight the application of three of our robust extensions on simulated and real-world data. Results suggest that in particular robustness w.r.t. model choice can lead to substantial accuracy gains.

Keywords

Cite

@article{arxiv.2303.01117,
  title  = {In all LikelihoodS: How to Reliably Select Pseudo-Labeled Data for Self-Training in Semi-Supervised Learning},
  author = {Julian Rodemann and Christoph Jansen and Georg Schollmeyer and Thomas Augustin},
  journal= {arXiv preprint arXiv:2303.01117},
  year   = {2023}
}

Comments

9 pages, 1 figure, under review

R2 v1 2026-06-28T08:56:31.574Z