Exploring Active Learning in Meta-Learning: Enhancing Context Set Labeling
Abstract
Most meta-learning methods assume that the (very small) context set used to establish a new task at test time is passively provided. In some settings, however, it is feasible to actively select which points to label; the potential gain from a careful choice is substantial, but the setting requires major differences from typical active learning setups. We clarify the ways in which active meta-learning can be used to label a context set, depending on which parts of the meta-learning process use active learning. Within this framework, we propose a natural algorithm based on fitting Gaussian mixtures for selecting which points to label; though simple, the algorithm also has theoretical motivation. The proposed algorithm outperforms state-of-the-art active learning methods when used with various meta-learning algorithms across several benchmark datasets.
Cite
Text
Bae et al. "Exploring Active Learning in Meta-Learning: Enhancing Context Set Labeling." Proceedings of the European Conference on Computer Vision (ECCV), 2024. doi:10.1007/978-3-031-73024-5_17Markdown
[Bae et al. "Exploring Active Learning in Meta-Learning: Enhancing Context Set Labeling." Proceedings of the European Conference on Computer Vision (ECCV), 2024.](https://mlanthology.org/eccv/2024/bae2024eccv-exploring/) doi:10.1007/978-3-031-73024-5_17BibTeX
@inproceedings{bae2024eccv-exploring,
title = {{Exploring Active Learning in Meta-Learning: Enhancing Context Set Labeling}},
author = {Bae, Wonho and Wang, Jing and Sutherland, Danica J.},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
year = {2024},
doi = {10.1007/978-3-031-73024-5_17},
url = {https://mlanthology.org/eccv/2024/bae2024eccv-exploring/}
}