Deep active learning with adaptive acquisition

• Verfasst von: Haußmann, Manuel [VerfasserIn]
• Verfasst von: Hamprecht, Fred [VerfasserIn]
• Verfasst von: Kandemir, Melih [VerfasserIn]
• Titel: Deep active learning with adaptive acquisition
• Verf.angabe: Manuel Haußmann, Fred Hamprecht and Melih Kandemir
• E-Jahr: 2019
• Jahr: 27 Jun 2019
• Umfang: 7 S.
• Fussnoten: Gesehen am 13.07.2022
• Titel Quelle: Enthalten in: De.arxiv.org
• Ort Quelle: [S.l.] : Arxiv.org, 1991
• Jahr Quelle: 2019
• Band/Heft Quelle: (2019), Artikel-ID 1906.11471, Seite 1-7
• DOI: doi:10.48550/arXiv.1906.11471
• Datenträger: Online-Ressource
• Sprache: eng
• Sach-SW: Computer Science - Machine Learning
• Sach-SW: Statistics - Machine Learning
• K10plus-PPN: 1810087864

Abstract

Model selection is treated as a standard performance boosting step in many machine learning applications. Once all other properties of a learning problem are fixed, the model is selected by grid search on a held-out validation set. This is strictly inapplicable to active learning. Within the standardized workflow, the acquisition function is chosen among available heuristics a priori, and its success is observed only after the labeling budget is already exhausted. More importantly, none of the earlier studies report a unique consistently successful acquisition heuristic to the extent to stand out as the unique best choice. We present a method to break this vicious circle by defining the acquisition function as a learning predictor and training it by reinforcement feedback collected from each labeling round. As active learning is a scarce data regime, we bootstrap from a well-known heuristic that filters the bulk of data points on which all heuristics would agree, and learn a policy to warp the top portion of this ranking in the most beneficial way for the character of a specific data distribution. Our system consists of a Bayesian neural net, the predictor, a bootstrap acquisition function, a probabilistic state definition, and another Bayesian policy network that can effectively incorporate this input distribution. We observe on three benchmark data sets that our method always manages to either invent a new superior acquisition function or to adapt itself to the a priori unknown best performing heuristic for each specific data set.