Learning Algorithms for Active Learning

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.

Authors

• Philip Bachman
• Alessandro Sordoni
• Adam Trischler

Keywords

No keywords are indexed for this paper.