Counterfactual Active Learning for Out-of-Distribution Generalization

Xun Deng, Wenjie Wang, Fuli Feng, Hanwang Zhang, Xiangnan He, Yong Liao


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.
Anthology ID:
2023.acl-long.636
Volume:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
11362–11377
Language:
URL:
https://aclanthology.org/2023.acl-long.636
DOI:
10.18653/v1/2023.acl-long.636
Bibkey:
Cite (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.
Cite (Informal):
Counterfactual Active Learning for Out-of-Distribution Generalization (Deng et al., ACL 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/dois-2013-emnlp/2023.acl-long.636.pdf
Video:
 https://preview.aclanthology.org/dois-2013-emnlp/2023.acl-long.636.mp4