@inproceedings{deng-etal-2023-counterfactual,
title = "Counterfactual Active Learning for Out-of-Distribution Generalization",
author = "Deng, Xun and
Wang, Wenjie and
Feng, Fuli and
Zhang, Hanwang and
He, Xiangnan and
Liao, Yong",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-long.636",
doi = "10.18653/v1/2023.acl-long.636",
pages = "11362--11377",
abstract = "We study the out-of-distribution generalization of active learning that adaptively selects samples for annotation in learning the decision boundary of classification. Our empirical study finds that increasingly annotating seen samples may hardly benefit the generalization. To address the problem, we propose Counterfactual Active Learning (CounterAL) that empowers active learning with counterfactual thinking to bridge the seen samples with unseen cases. In addition to annotating factual samples, CounterAL requires annotators to answer counterfactual questions to construct counterfactual samples for training. To achieve CounterAL, we design a new acquisition strategy that selects the informative factual-counterfactual pairs for annotation; and a new training strategy that pushes the model update to focus on the discrepancy between factual and counterfactual samples. We evaluate CounterAL on multiple public datasets of sentiment analysis and natural language inference. The experiment results show that CounterAL requires fewer acquisition rounds and outperforms existing active learning methods by a large margin in OOD tests with comparable IID performance.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="deng-etal-2023-counterfactual">
<titleInfo>
<title>Counterfactual Active Learning for Out-of-Distribution Generalization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xun</namePart>
<namePart type="family">Deng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjie</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fuli</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hanwang</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiangnan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yong</namePart>
<namePart type="family">Liao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We study the out-of-distribution generalization of active learning that adaptively selects samples for annotation in learning the decision boundary of classification. Our empirical study finds that increasingly annotating seen samples may hardly benefit the generalization. To address the problem, we propose Counterfactual Active Learning (CounterAL) that empowers active learning with counterfactual thinking to bridge the seen samples with unseen cases. In addition to annotating factual samples, CounterAL requires annotators to answer counterfactual questions to construct counterfactual samples for training. To achieve CounterAL, we design a new acquisition strategy that selects the informative factual-counterfactual pairs for annotation; and a new training strategy that pushes the model update to focus on the discrepancy between factual and counterfactual samples. We evaluate CounterAL on multiple public datasets of sentiment analysis and natural language inference. The experiment results show that CounterAL requires fewer acquisition rounds and outperforms existing active learning methods by a large margin in OOD tests with comparable IID performance.</abstract>
<identifier type="citekey">deng-etal-2023-counterfactual</identifier>
<identifier type="doi">10.18653/v1/2023.acl-long.636</identifier>
<location>
<url>https://aclanthology.org/2023.acl-long.636</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>11362</start>
<end>11377</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Counterfactual Active Learning for Out-of-Distribution Generalization
%A Deng, Xun
%A Wang, Wenjie
%A Feng, Fuli
%A Zhang, Hanwang
%A He, Xiangnan
%A Liao, Yong
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F deng-etal-2023-counterfactual
%X We study the out-of-distribution generalization of active learning that adaptively selects samples for annotation in learning the decision boundary of classification. Our empirical study finds that increasingly annotating seen samples may hardly benefit the generalization. To address the problem, we propose Counterfactual Active Learning (CounterAL) that empowers active learning with counterfactual thinking to bridge the seen samples with unseen cases. In addition to annotating factual samples, CounterAL requires annotators to answer counterfactual questions to construct counterfactual samples for training. To achieve CounterAL, we design a new acquisition strategy that selects the informative factual-counterfactual pairs for annotation; and a new training strategy that pushes the model update to focus on the discrepancy between factual and counterfactual samples. We evaluate CounterAL on multiple public datasets of sentiment analysis and natural language inference. The experiment results show that CounterAL requires fewer acquisition rounds and outperforms existing active learning methods by a large margin in OOD tests with comparable IID performance.
%R 10.18653/v1/2023.acl-long.636
%U https://aclanthology.org/2023.acl-long.636
%U https://doi.org/10.18653/v1/2023.acl-long.636
%P 11362-11377
Markdown (Informal)
[Counterfactual Active Learning for Out-of-Distribution Generalization](https://aclanthology.org/2023.acl-long.636) (Deng et al., ACL 2023)
ACL
- Xun Deng, Wenjie Wang, Fuli Feng, Hanwang Zhang, Xiangnan He, and Yong Liao. 2023. Counterfactual Active Learning for Out-of-Distribution Generalization. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 11362–11377, Toronto, Canada. Association for Computational Linguistics.