@inproceedings{lesci-vlachos-2024-anchoral,
title = "{A}nchor{AL}: Computationally Efficient Active Learning for Large and Imbalanced Datasets",
author = "Lesci, Pietro and
Vlachos, Andreas",
editor = "Duh, Kevin and
Gomez, Helena and
Bethard, Steven",
booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.naacl-long.467",
doi = "10.18653/v1/2024.naacl-long.467",
pages = "8445--8464",
abstract = "Active learning for imbalanced classification tasks is challenging as the minority classes naturally occur rarely. Gathering a large pool of unlabelled data is thus essential to capture minority instances. Standard pool-based active learning is computationally expensive on large pools and often reaches low accuracy by overfitting the initial decision boundary, thus failing to explore the input space and find minority instances. To address these issues we propose AnchorAL. At each iteration, AnchorAL chooses class-specific instances from the labelled set, or *anchors*, and retrieves the most similar unlabelled instances from the pool. This resulting *subpool* is then used for active learning. Using a small, fixed-sized subpool AnchorAL allows scaling any active learning strategy to large pools. By dynamically selecting different anchors at each iteration it promotes class balance and prevents overfitting the initial decision boundary, thus promoting the discovery of new clusters of minority instances. Experiments across different classification tasks, active learning strategies, and model architectures AnchorAL is *(i)* faster, often reducing runtime from hours to minutes, *(ii)* trains more performant models, *(iii)* and returns more balanced datasets than competing methods.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lesci-vlachos-2024-anchoral">
<titleInfo>
<title>AnchorAL: Computationally Efficient Active Learning for Large and Imbalanced Datasets</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pietro</namePart>
<namePart type="family">Lesci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Vlachos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Duh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Gomez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Active learning for imbalanced classification tasks is challenging as the minority classes naturally occur rarely. Gathering a large pool of unlabelled data is thus essential to capture minority instances. Standard pool-based active learning is computationally expensive on large pools and often reaches low accuracy by overfitting the initial decision boundary, thus failing to explore the input space and find minority instances. To address these issues we propose AnchorAL. At each iteration, AnchorAL chooses class-specific instances from the labelled set, or *anchors*, and retrieves the most similar unlabelled instances from the pool. This resulting *subpool* is then used for active learning. Using a small, fixed-sized subpool AnchorAL allows scaling any active learning strategy to large pools. By dynamically selecting different anchors at each iteration it promotes class balance and prevents overfitting the initial decision boundary, thus promoting the discovery of new clusters of minority instances. Experiments across different classification tasks, active learning strategies, and model architectures AnchorAL is *(i)* faster, often reducing runtime from hours to minutes, *(ii)* trains more performant models, *(iii)* and returns more balanced datasets than competing methods.</abstract>
<identifier type="citekey">lesci-vlachos-2024-anchoral</identifier>
<identifier type="doi">10.18653/v1/2024.naacl-long.467</identifier>
<location>
<url>https://aclanthology.org/2024.naacl-long.467</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>8445</start>
<end>8464</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AnchorAL: Computationally Efficient Active Learning for Large and Imbalanced Datasets
%A Lesci, Pietro
%A Vlachos, Andreas
%Y Duh, Kevin
%Y Gomez, Helena
%Y Bethard, Steven
%S Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F lesci-vlachos-2024-anchoral
%X Active learning for imbalanced classification tasks is challenging as the minority classes naturally occur rarely. Gathering a large pool of unlabelled data is thus essential to capture minority instances. Standard pool-based active learning is computationally expensive on large pools and often reaches low accuracy by overfitting the initial decision boundary, thus failing to explore the input space and find minority instances. To address these issues we propose AnchorAL. At each iteration, AnchorAL chooses class-specific instances from the labelled set, or *anchors*, and retrieves the most similar unlabelled instances from the pool. This resulting *subpool* is then used for active learning. Using a small, fixed-sized subpool AnchorAL allows scaling any active learning strategy to large pools. By dynamically selecting different anchors at each iteration it promotes class balance and prevents overfitting the initial decision boundary, thus promoting the discovery of new clusters of minority instances. Experiments across different classification tasks, active learning strategies, and model architectures AnchorAL is *(i)* faster, often reducing runtime from hours to minutes, *(ii)* trains more performant models, *(iii)* and returns more balanced datasets than competing methods.
%R 10.18653/v1/2024.naacl-long.467
%U https://aclanthology.org/2024.naacl-long.467
%U https://doi.org/10.18653/v1/2024.naacl-long.467
%P 8445-8464
Markdown (Informal)
[AnchorAL: Computationally Efficient Active Learning for Large and Imbalanced Datasets](https://aclanthology.org/2024.naacl-long.467) (Lesci & Vlachos, NAACL 2024)
ACL