Recent Advancements in Active Learning
Mathematics · 18.04.2026 · 14 (8) · 1358
DOI: 10.3390/math14081358 ↗Kurz gefasst
Fachartikel in der Zeitschrift Mathematics, online erschienen am 18.04.2026. Verfasst von Bokyung Amy Kwon und 1 weiteren Autor:innen. Die Arbeit nennt 64 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NRF, Hanyang University ERICA, IITP.
Abstract (Originalsprache)
Active learning (AL) aims to maximize model performance while minimizing annotation costs. With the rapid adoption of deep learning, AL approaches have evolved to meet contemporary demands. We systematically examine the literature published from 2018 to May 2025, focusing on four key trends: batch-mode selection, transfer learning integration, multi-strategy querying, and extension to diverse application domains. In addition, we summarize classical AL approaches. While observations show that combining AL with deep learning significantly enhances data efficiency, a critical limitation remains: the lack of standardized evaluation protocols across studies hinders precise comparisons. Nevertheless, we find that AL is well-aligned with modern trends, and we offer insights into underexplored opportunities to guide future research within the machine learning community.
Förderung
- NRF
- Hanyang University ERICA
- IITP
Zitieren
APA
Kwon, B. A., & Kang, K. (2026). Recent Advancements in Active Learning. Mathematics, 14(8), 1358. https://doi.org/10.3390/math14081358
Vancouver
Kwon BA, Kang K. Recent Advancements in Active Learning. Mathematics. 2026;14(8):1358. doi:10.3390/math14081358
BibTeX
@article{Kwon2026,
author = {Kwon, Bokyung Amy and Kang, Kyungtae},
title = {Recent Advancements in Active Learning},
journal = {Mathematics},
year = {2026},
volume = {14},
number = {8},
pages = {1358},
doi = {10.3390/math14081358}
}
EUVIMED