Timezone: »

 
Spotlight
Online Active Learning with Surrogate Loss Functions
Giulia DeSalvo · Claudio Gentile · Tobias Sommer Thune

@

We derive a novel active learning algorithm in the streaming setting for binary classification tasks. The algorithm leverages weak labels to minimize the number of label requests, and trains a model to optimize a surrogate loss on a resulting set of labeled and weak-labeled points. Our algorithm jointly admits two crucial properties: theoretical guarantees in the general agnostic setting and a strong empirical performance. Our theoretical analysis shows that the algorithm attains favorable generalization and label complexity bounds, while our empirical study on 18 real-world datasets demonstrate that the algorithm outperforms standard baselines, including the Margin Algorithm, or Uncertainty Sampling, a high-performing active learning algorithm favored by practitioners.

Author Information

Giulia DeSalvo (Google Research)
Claudio Gentile (Google Research)
Tobias Sommer Thune (University of Copenhagen)

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

More from the Same Authors