Region-Based Active Learning

Corinna Cortes, Giulia DeSalvo, Claudio Gentile, Mehryar Mohri, Ningshan Zhang
Proceedings of the Twenty-Second International Conference on Artificial Intelligence and Statistics, PMLR 89:2801-2809, 2019.

Abstract

We study a scenario of active learning where the input space is partitioned into different regions and where a distinct hypothesis is learned for each region. We first introduce a new active learning algorithm (EIWAL), which is an enhanced version of the IWAL algorithm, based on a finer analysis that results in more favorable learning guarantees. Then, we present a new learning algorithm for region-based active learning, ORIWAL, in which either IWAL or EIWAL serve as a subroutine. ORIWAL optimally allocates points to the subroutine algorithm for each region. We give a detailed theoretical analysis of ORIWAL, including generalization error guarantees and bounds on the number of points labeled, in terms of both the hypothesis set used in each region and the probability mass of that region. We also report the results of several experiments for our algorithm which demonstrate substantial benefits over existing non-region-based active learning algorithms, such as IWAL, and over passive learning.

Cite this Paper

BibTeX
@InProceedings{pmlr-v89-cortes19a, title = {Region-Based Active Learning}, author = {Cortes, Corinna and DeSalvo, Giulia and Gentile, Claudio and Mohri, Mehryar and Zhang, Ningshan}, booktitle = {Proceedings of the Twenty-Second International Conference on Artificial Intelligence and Statistics}, pages = {2801--2809}, year = {2019}, editor = {Chaudhuri, Kamalika and Sugiyama, Masashi}, volume = {89}, series = {Proceedings of Machine Learning Research}, month = {16--18 Apr}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v89/cortes19a/cortes19a.pdf}, url = {https://proceedings.mlr.press/v89/cortes19a.html}, abstract = {We study a scenario of active learning where the input space is partitioned into different regions and where a distinct hypothesis is learned for each region. We first introduce a new active learning algorithm (EIWAL), which is an enhanced version of the IWAL algorithm, based on a finer analysis that results in more favorable learning guarantees. Then, we present a new learning algorithm for region-based active learning, ORIWAL, in which either IWAL or EIWAL serve as a subroutine. ORIWAL optimally allocates points to the subroutine algorithm for each region. We give a detailed theoretical analysis of ORIWAL, including generalization error guarantees and bounds on the number of points labeled, in terms of both the hypothesis set used in each region and the probability mass of that region. We also report the results of several experiments for our algorithm which demonstrate substantial benefits over existing non-region-based active learning algorithms, such as IWAL, and over passive learning.} }
Endnote
%0 Conference Paper %T Region-Based Active Learning %A Corinna Cortes %A Giulia DeSalvo %A Claudio Gentile %A Mehryar Mohri %A Ningshan Zhang %B Proceedings of the Twenty-Second International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2019 %E Kamalika Chaudhuri %E Masashi Sugiyama %F pmlr-v89-cortes19a %I PMLR %P 2801--2809 %U https://proceedings.mlr.press/v89/cortes19a.html %V 89 %X We study a scenario of active learning where the input space is partitioned into different regions and where a distinct hypothesis is learned for each region. We first introduce a new active learning algorithm (EIWAL), which is an enhanced version of the IWAL algorithm, based on a finer analysis that results in more favorable learning guarantees. Then, we present a new learning algorithm for region-based active learning, ORIWAL, in which either IWAL or EIWAL serve as a subroutine. ORIWAL optimally allocates points to the subroutine algorithm for each region. We give a detailed theoretical analysis of ORIWAL, including generalization error guarantees and bounds on the number of points labeled, in terms of both the hypothesis set used in each region and the probability mass of that region. We also report the results of several experiments for our algorithm which demonstrate substantial benefits over existing non-region-based active learning algorithms, such as IWAL, and over passive learning.
APA
Cortes, C., DeSalvo, G., Gentile, C., Mohri, M. & Zhang, N.. (2019). Region-Based Active Learning. Proceedings of the Twenty-Second International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 89:2801-2809 Available from https://proceedings.mlr.press/v89/cortes19a.html.

Related Material