ICML 2017poster215 citations

Learning Algorithms for Active Learning

Philip Bachman, Alessandro Sordoni, Adam Trischler

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.

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.}
}
Learning Algorithms for Active Learning · ICML 2017