Timezone: »

Learning Algorithms for Active Learning
Philip Bachman · Alessandro Sordoni · Adam Trischler

Tue Aug 08 01:30 AM -- 05:00 AM (PDT) @ Gallery #21

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.

Author Information

Philip Bachman (Maluuba)
Alessandro Sordoni (Microsoft Maluuba)
Adam Trischler (Maluuba)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors