Timezone: »
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)
-
2021 Poster: Online Active Learning with Surrogate Loss Functions »
Fri. Dec 10th 04:30 -- 06:00 PM Room
More from the Same Authors
-
2023 Poster: Easy Learning from Label Proportions »
Róbert Busa-Fekete · Heejin Choi · Travis Dick · Claudio Gentile · Andres Munoz Medina -
2022 Poster: Best of Both Worlds Model Selection »
Aldo Pacchiano · Christoph Dann · Claudio Gentile -
2022 Poster: Regret Bounds for Multilabel Classification in Sparse Label Regimes »
Róbert Busa-Fekete · Heejin Choi · Krzysztof Dembczynski · Claudio Gentile · Henry Reeve · Balazs Szorenyi -
2021 Poster: Batch Active Learning at Scale »
Gui Citovsky · Giulia DeSalvo · Claudio Gentile · Lazaros Karydas · Anand Rajagopalan · Afshin Rostamizadeh · Sanjiv Kumar -
2021 Poster: Learning with Labeling Induced Abstentions »
Kareem Amin · Giulia DeSalvo · Afshin Rostamizadeh -
2021 Poster: Neural Active Learning with Performance Guarantees »
Zhilei Wang · Pranjal Awasthi · Christoph Dann · Ayush Sekhari · Claudio Gentile -
2019 Poster: Flattening a Hierarchical Clustering through Active Learning »
Fabio Vitale · Anand Rajagopalan · Claudio Gentile -
2019 Poster: Nonstochastic Multiarmed Bandits with Unrestricted Delays »
Tobias Sommer Thune · Nicolò Cesa-Bianchi · Yevgeny Seldin -
2018 Poster: Adaptation to Easy Data in Prediction with Limited Advice »
Tobias Sommer Thune · Yevgeny Seldin -
2018 Poster: Online Reciprocal Recommendation with Theoretical Performance Guarantees »
Claudio Gentile · Nikos Parotsidis · Fabio Vitale