Online Active Learning with Surrogate Loss Functions

Part of Advances in Neural Information Processing Systems 34 (NeurIPS 2021)

Bibtex Paper Reviews And Public Comment » Supplemental

Authors

Giulia DeSalvo, Claudio Gentile, Tobias Sommer Thune

Abstract

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.