EUVIMEDEUVIMED entdecken
Crossref

Active Learning for Multiple Target Models

Sheng-Jun Huang, Yi Li, Ying-Peng Tang

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2026-01 · 48 (1) · 140-154

DOI: 10.1109/tpami.2025.3602682 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026-01. Verfasst von Sheng-Jun Huang und 2 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 71 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Singapore Ministry of Education AcRF Tier 2, NeurIPS 2022.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We present a novel setting of active learning (AL) where multiple target models are simultaneously learned. This setting arises in real-world applications where machine learning systems require training multiple models on the same labeled dataset to accommodate diverse devices with varying computational resources. However, traditional AL methods are often limited by their model dependence and non-transferability. In this paper, we address the question of whether an effective AL method can be designed for multiple target models. We analyze the query complexity of active and passive learning in this setting and demonstrate the potential for AL to achieve improved query complexity. Based on this insight, we further propose an agnostic AL sampling strategy which selects examples located in the joint disagreement regions of different target models. Experimental evaluations on classification and regression benchmarks validate the effectiveness of our approach over traditional AL methods.

Förderung

  • National Natural Science Foundation of China
  • Singapore Ministry of Education AcRF Tier 2
  • NeurIPS 2022

Zitieren

APA

Huang, S. J., Li, Y., & Tang, Y. P. (2026). Active Learning for Multiple Target Models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 48(1), 140-154. https://doi.org/10.1109/tpami.2025.3602682

Vancouver

Huang SJ, Li Y, Tang YP. Active Learning for Multiple Target Models. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2026;48(1):140-154. doi:10.1109/tpami.2025.3602682

BibTeX
@article{Huang2026,
  author = {Huang, Sheng-Jun and Li, Yi and Tang, Ying-Peng},
  title = {Active Learning for Multiple Target Models},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2026},
  volume = {48},
  number = {1},
  pages = {140--154},
  doi = {10.1109/tpami.2025.3602682}
}
Kostenlos starten →