A Survey on Active Learning: State-of-the-Art, Practical Challenges and Research Directions
Mathematics · 06.02.2023 · 11 (4) · 820
DOI: 10.3390/math11040820 ↗Kurz gefasst
Fachartikel in der Zeitschrift Mathematics, online erschienen am 06.02.2023. Verfasst von Alaa Tharwat und 1 weiteren Autor:innen. Die Arbeit wurde bisher 186-mal zitiert (Crossref) und nennt 220 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: SustAInable Lifecycle of Intelligent Socio-Technical Systems.
Abstract (Originalsprache)
Despite the availability and ease of collecting a large amount of free, unlabeled data, the expensive and time-consuming labeling process is still an obstacle to labeling a sufficient amount of training data, which is essential for building supervised learning models. Here, with low labeling cost, the active learning (AL) technique could be a solution, whereby a few, high-quality data points are queried by searching for the most informative and representative points within the instance space. This strategy ensures high generalizability across the space and improves classification performance on data we have never seen before. In this paper, we provide a survey of recent studies on active learning in the context of classification. This survey starts with an introduction to the theoretical background of the AL technique, AL scenarios, AL components supported with visual explanations, and illustrative examples to explain how AL simply works and the benefits of using AL. In addition to an overview of the query strategies for the classification scenarios, this survey provides a high-level summary to explain various practical challenges with AL in real-world settings; it also explains how AL can be combined with various research areas. Finally, the most commonly used AL software packages and experimental evaluation metrics with AL are also discussed.
Förderung
- SustAInable Lifecycle of Intelligent Socio-Technical Systems
Zitieren
APA
Tharwat, A., & Schenck, W. (2023). A Survey on Active Learning: State-of-the-Art, Practical Challenges and Research Directions. Mathematics, 11(4), 820. https://doi.org/10.3390/math11040820
Vancouver
Tharwat A, Schenck W. A Survey on Active Learning: State-of-the-Art, Practical Challenges and Research Directions. Mathematics. 2023;11(4):820. doi:10.3390/math11040820
BibTeX
@article{Tharwat2023,
author = {Tharwat, Alaa and Schenck, Wolfram},
title = {A Survey on Active Learning: State-of-the-Art, Practical Challenges and Research Directions},
journal = {Mathematics},
year = {2023},
volume = {11},
number = {4},
pages = {820},
doi = {10.3390/math11040820}
}
EUVIMED