Adaptive Region-Based Active Learning

Corinna Cortes, Giulia Desalvo, Claudio Gentile, Mehryar Mohri, Ningshan Zhang
Proceedings of the 37th International Conference on Machine Learning, PMLR 119:2144-2153, 2020.

Abstract

We present a new active learning algorithm that adaptively partitions the input space into a finite number of regions, and subsequently seeks a distinct predictor for each region, while actively requesting labels. We prove theoretical guarantees for both the generalization error and the label complexity of our algorithm, and analyze the number of regions defined by the algorithm under some mild assumptions. We also report the results of an extensive suite of experiments on several real-world datasets demonstrating substantial empirical benefits over existing single-region and non-adaptive region-based active learning baselines.

Cite this Paper


BibTeX
@InProceedings{pmlr-v119-cortes20a, title = {Adaptive Region-Based Active Learning}, author = {Cortes, Corinna and Desalvo, Giulia and Gentile, Claudio and Mohri, Mehryar and Zhang, Ningshan}, booktitle = {Proceedings of the 37th International Conference on Machine Learning}, pages = {2144--2153}, year = {2020}, editor = {III, Hal Daumé and Singh, Aarti}, volume = {119}, series = {Proceedings of Machine Learning Research}, month = {13--18 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v119/cortes20a/cortes20a.pdf}, url = {https://proceedings.mlr.press/v119/cortes20a.html}, abstract = {We present a new active learning algorithm that adaptively partitions the input space into a finite number of regions, and subsequently seeks a distinct predictor for each region, while actively requesting labels. We prove theoretical guarantees for both the generalization error and the label complexity of our algorithm, and analyze the number of regions defined by the algorithm under some mild assumptions. We also report the results of an extensive suite of experiments on several real-world datasets demonstrating substantial empirical benefits over existing single-region and non-adaptive region-based active learning baselines.} }
Endnote
%0 Conference Paper %T Adaptive Region-Based Active Learning %A Corinna Cortes %A Giulia Desalvo %A Claudio Gentile %A Mehryar Mohri %A Ningshan Zhang %B Proceedings of the 37th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2020 %E Hal Daumé III %E Aarti Singh %F pmlr-v119-cortes20a %I PMLR %P 2144--2153 %U https://proceedings.mlr.press/v119/cortes20a.html %V 119 %X We present a new active learning algorithm that adaptively partitions the input space into a finite number of regions, and subsequently seeks a distinct predictor for each region, while actively requesting labels. We prove theoretical guarantees for both the generalization error and the label complexity of our algorithm, and analyze the number of regions defined by the algorithm under some mild assumptions. We also report the results of an extensive suite of experiments on several real-world datasets demonstrating substantial empirical benefits over existing single-region and non-adaptive region-based active learning baselines.
APA
Cortes, C., Desalvo, G., Gentile, C., Mohri, M. & Zhang, N.. (2020). Adaptive Region-Based Active Learning. Proceedings of the 37th International Conference on Machine Learning, in Proceedings of Machine Learning Research 119:2144-2153 Available from https://proceedings.mlr.press/v119/cortes20a.html.

Related Material