IALE: Imitating Active Learner Ensembles
Löffler C, Mutschler C (2022)
Publication Language: English
Publication Type: Journal article, Original article
Publication year: 2022
Journal
Book Volume: 23
Pages Range: 1-29
Article Number: 107
URI: http://jmlr.org/papers/v23/21-0387.html
Open Access Link: https://www.jmlr.org/papers/volume23/21-0387/21-0387.pdf
Abstract
Active learning prioritizes the labeling of the most informative data samples. However, the performance of active learning heuristics depends on both the structure of the underlying model architecture and the data. We propose IALE, an imitation learning scheme that imitates the selection of the best-performing expert heuristic at each stage of the learning cycle in a batch-mode pool-based setting. We use Dagger to train a transferable policy on a dataset and later apply it to different datasets and deep classifier architectures. The policy reflects on the best choices from multiple expert heuristics given the current state of the active learning process, and learns to select samples in a complementary way that unifies the expert strategies. Our experiments on well-known image datasets show that we outperform state of the art imitation learners and heuristics.
Authors with CRIS profile
Related research project(s)
Involved external institutions
Germany (DE)How to cite
APA:
Löffler, C., & Mutschler, C. (2022). IALE: Imitating Active Learner Ensembles. Journal of Machine Learning Research, 23, 1-29.
MLA:
Löffler, Christoffer, and Christopher Mutschler. "IALE: Imitating Active Learner Ensembles." Journal of Machine Learning Research 23 (2022): 1-29.
BibTeX: Download