Learning Algorithms for Active Learning
Abstract
We introduce a model that learns active learning algorithms via metalearning. For a distribution of related tasks, our model jointly learns: a data representation, an item selection heuristic, and a prediction function. Our model uses the item selection heuristic to construct a labeled support set for training the prediction function. Using the Omniglot and MovieLens datasets, we test our model in synthetic and practical settings.
Cite
Text
Bachman et al. "Learning Algorithms for Active Learning." International Conference on Learning Representations, 2017.Markdown
[Bachman et al. "Learning Algorithms for Active Learning." International Conference on Learning Representations, 2017.](https://mlanthology.org/iclr/2017/bachman2017iclr-learning/)BibTeX
@inproceedings{bachman2017iclr-learning,
title = {{Learning Algorithms for Active Learning}},
author = {Bachman, Philip and Sordoni, Alessandro and Trischler, Adam},
booktitle = {International Conference on Learning Representations},
year = {2017},
url = {https://mlanthology.org/iclr/2017/bachman2017iclr-learning/}
}