Home > Research > Publications & Outputs > Semi-supervised Learning Guided by the Generali...

Links

Text available via DOI:

View graph of relations

Semi-supervised Learning Guided by the Generalized Bayes Rule Under Soft Revision

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Published

Standard

Semi-supervised Learning Guided by the Generalized Bayes Rule Under Soft Revision. / Dietrich, Stefan; Rodemann, Julian; Jansen, Christoph.
Combining, Modelling and Analyzing Imprecision, Randomness and Dependence. Cham: Springer, 2024. p. 110-117 (Advances in Intelligent Systems and Computing (AISC); Vol. 1458).

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Harvard

Dietrich, S, Rodemann, J & Jansen, C 2024, Semi-supervised Learning Guided by the Generalized Bayes Rule Under Soft Revision. in Combining, Modelling and Analyzing Imprecision, Randomness and Dependence. Advances in Intelligent Systems and Computing (AISC), vol. 1458, Springer, Cham, pp. 110-117. https://doi.org/10.1007/978-3-031-65993-5_13

APA

Dietrich, S., Rodemann, J., & Jansen, C. (2024). Semi-supervised Learning Guided by the Generalized Bayes Rule Under Soft Revision. In Combining, Modelling and Analyzing Imprecision, Randomness and Dependence (pp. 110-117). (Advances in Intelligent Systems and Computing (AISC); Vol. 1458). Springer. https://doi.org/10.1007/978-3-031-65993-5_13

Vancouver

Dietrich S, Rodemann J, Jansen C. Semi-supervised Learning Guided by the Generalized Bayes Rule Under Soft Revision. In Combining, Modelling and Analyzing Imprecision, Randomness and Dependence. Cham: Springer. 2024. p. 110-117. (Advances in Intelligent Systems and Computing (AISC)). doi: 10.1007/978-3-031-65993-5_13

Author

Dietrich, Stefan ; Rodemann, Julian ; Jansen, Christoph. / Semi-supervised Learning Guided by the Generalized Bayes Rule Under Soft Revision. Combining, Modelling and Analyzing Imprecision, Randomness and Dependence. Cham : Springer, 2024. pp. 110-117 (Advances in Intelligent Systems and Computing (AISC)).

Bibtex

@inproceedings{ded7738e40e94332a971bb0c779ae907,
title = "Semi-supervised Learning Guided by the Generalized Bayes Rule Under Soft Revision",
abstract = "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.",
author = "Stefan Dietrich and Julian Rodemann and Christoph Jansen",
year = "2024",
month = aug,
day = "10",
doi = "10.1007/978-3-031-65993-5_13",
language = "English",
isbn = "9783031659928",
series = "Advances in Intelligent Systems and Computing (AISC)",
publisher = "Springer",
pages = "110--117",
booktitle = "Combining, Modelling and Analyzing Imprecision, Randomness and Dependence",

}

RIS

TY - GEN

T1 - Semi-supervised Learning Guided by the Generalized Bayes Rule Under Soft Revision

AU - Dietrich, Stefan

AU - Rodemann, Julian

AU - Jansen, Christoph

PY - 2024/8/10

Y1 - 2024/8/10

N2 - 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.

AB - 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.

U2 - 10.1007/978-3-031-65993-5_13

DO - 10.1007/978-3-031-65993-5_13

M3 - Conference contribution/Paper

SN - 9783031659928

T3 - Advances in Intelligent Systems and Computing (AISC)

SP - 110

EP - 117

BT - Combining, Modelling and Analyzing Imprecision, Randomness and Dependence

PB - Springer

CY - Cham

ER -