Learning Algorithms for Active Learning
Machine Learning
2017-08-02 v1
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 method for constructing prediction functions from labeled training sets. Our model uses the item selection heuristic to gather labeled training sets from which to construct prediction functions. Using the Omniglot and MovieLens datasets, we test our model in synthetic and practical settings.
Cite
@article{arxiv.1708.00088,
title = {Learning Algorithms for Active Learning},
author = {Philip Bachman and Alessandro Sordoni and Adam Trischler},
journal= {arXiv preprint arXiv:1708.00088},
year = {2017}
}
Comments
Accepted for publication at ICML 2017