Asymptotic Optimality for Active Learning Processes

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review

View graph of relations

Author(s)

Related Research Unit(s)

Detail(s)

Original languageEnglish
Title of host publicationProceedings of the 38th Conference on Uncertainty in Artificial Intelligence (UAI 2022)
PublisherPMLR
Pages2342-2352
Volume180
ISBN (Print)9781713863298
Publication statusPublished - Aug 2022

Publication series

NameProceedings of Machine Learning Research
ISSN (Print)2640-3498

Conference

Title38th Conference on Uncertainty in Artificial Intelligence (UAI 2022)
LocationIn-person in Eindhoven and also online
PlaceNetherlands
CityEindhoven
Period1 August 2002 - 5 August 2022

Abstract

Active Learning (AL) aims to optimize basic learned model(s) iteratively by selecting and annotating unlabeled data samples that are deemed to best maximise the model performance with minimal required data. However, the learned model is easy to overfit due to the biased distribution (sampling bias and dataset shift) formed by nonuniform sampling used in AL. Considering AL as an iterative sequential optimization process, we first provide a perspective on AL in terms of statistical properties, i.e., asymptotic unbiasedness, consistency and asymptotic efficiency, with respect to basic estimators when the sample size (size of labeled set) becomes large, and in the limit as sample size tends to infinity. We then discuss how biases affect AL. Finally, we proposed a flexible AL framework that aims to mitigate the impact of bias in AL by minimizing generalization error and importance-weighted training loss simultaneously. © 2022 UAI. All Rights Reserved.

Citation Format(s)

Asymptotic Optimality for Active Learning Processes. / Zhan, Xueying; Wang, Yaowei; Chan, Antoni B.
Proceedings of the 38th Conference on Uncertainty in Artificial Intelligence (UAI 2022). Vol. 180 PMLR, 2022. p. 2342-2352 (Proceedings of Machine Learning Research).

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review