Uncertainty-guided Active Learning with Theoretical Bounds on Label Complexity
ACM Transactions on Probabilistic Machine Learning · 2025
DOI: 10.1145/3728716 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Probabilistic Machine Learning, 2025. Verfasst von Deepesh Agarwal und 1 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 47 Literaturangaben. Gefördert von: National Science Foundation.
Abstract (Originalsprache)
In recent years, neural networks (NNs) have been embraced by several scientific and engineering disciplines for diverse modeling and inferencing applications. The importance of quantifying the confidence in NN predictions has escalated due to the increasing adoption of these decision models. Nevertheless, conventional NN do not furnish uncertainty estimates associated with their predictions and are therefore ill-calibrated. Uncertainty quantification techniques offer probability distributions or CIs to represent the uncertainty associated with NN predictions, instead of solely presenting the point predictions/estimates. Once the uncertainty in NN is quantified, it is crucial to leverage this information to modify training objectives and improve the accuracy and reliability of the corresponding decision models. This work presents a novel framework to utilize the knowledge of input and output uncertainties in NN to guide querying process in the context of Active Learning. We also derive the lower and upper bounds for label complexity. The efficacy of the proposed framework is established by conducting experiments across classification and regression tasks.
Förderung
- National Science Foundation
Zitieren
APA
Agarwal, D., & Natarajan, B. (2025). Uncertainty-guided Active Learning with Theoretical Bounds on Label Complexity. ACM Transactions on Probabilistic Machine Learning. https://doi.org/10.1145/3728716
Vancouver
Agarwal D, Natarajan B. Uncertainty-guided Active Learning with Theoretical Bounds on Label Complexity. ACM Transactions on Probabilistic Machine Learning. 2025. doi:10.1145/3728716
BibTeX
@article{Agarwal2025,
author = {Agarwal, Deepesh and Natarajan, Balasubramaniam},
title = {Uncertainty-guided Active Learning with Theoretical Bounds on Label Complexity},
journal = {ACM Transactions on Probabilistic Machine Learning},
year = {2025},
doi = {10.1145/3728716}
}
EUVIMED