Learning Algorithms for Active Learning

Philip Bachman, Alessandro Sordoni, Adam Trischler
Proceedings of the 34th International Conference on Machine Learning, PMLR 70:301-310, 2017.

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 this Paper

BibTeX
@InProceedings{pmlr-v70-bachman17a, title = {Learning Algorithms for Active Learning}, author = {Philip Bachman and Alessandro Sordoni and Adam Trischler}, booktitle = {Proceedings of the 34th International Conference on Machine Learning}, pages = {301--310}, year = {2017}, editor = {Precup, Doina and Teh, Yee Whye}, volume = {70}, series = {Proceedings of Machine Learning Research}, month = {06--11 Aug}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v70/bachman17a/bachman17a.pdf}, url = {https://proceedings.mlr.press/v70/bachman17a.html}, 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.} }
Endnote
%0 Conference Paper %T Learning Algorithms for Active Learning %A Philip Bachman %A Alessandro Sordoni %A Adam Trischler %B Proceedings of the 34th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2017 %E Doina Precup %E Yee Whye Teh %F pmlr-v70-bachman17a %I PMLR %P 301--310 %U https://proceedings.mlr.press/v70/bachman17a.html %V 70 %X 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.
APA
Bachman, P., Sordoni, A. & Trischler, A.. (2017). Learning Algorithms for Active Learning. Proceedings of the 34th International Conference on Machine Learning, in Proceedings of Machine Learning Research 70:301-310 Available from https://proceedings.mlr.press/v70/bachman17a.html.

Related Material