Certifiable Active Class Selection in Multi-Class Classification

Active class selection (ACS) requires the developer of a classifier to actively choose the class proportions of the training data. This
freedom of choice puts the trust in the trained classifier at risk if the true class proportions, which occur during deployment, are subject to uncertainties. This issue has recently motivated a certificate for ACS-trained classifiers, which builds trust by proving that a classifier is sufficiently correct within a specific set of class proportions and with a high probability. However, this certificate was only developed in the context of binary classification. In this paper, we employ Hölder’s inequality to extend the binary ACS certificate to multi-class settings. We demonstrate that our extension indeed provides correct and tight upper bounds of the classifier’s error. We conclude with several directions for future work.

  • Published in:
    Workshop on Interactive Adaptive Learning at the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases
  • Type:
    Inproceedings
  • Authors:
    Senz, Martin; Bunse, Mirko; Morik, Katharina
  • Year:
    2022

Citation information

Senz, Martin; Bunse, Mirko; Morik, Katharina: Certifiable Active Class Selection in Multi-Class Classification, Workshop on Interactive Adaptive Learning at the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2022, Senz.etal.2022a,

Associated Lamarr Researchers

lamarr institute person Morik Katharina e1663924705259 - Lamarr Institute for Machine Learning (ML) and Artificial Intelligence (AI)

Prof. Dr. Katharina Morik

Founding Director to the profile