Counterfactual Adversarial Learning with Representation Interpolation
Wei Wang, Boxin Wang, Ning Shi, Jinfeng Li, Bingyu Zhu, Xiangyu Liu, Rong Zhang
Abstract
Deep learning models exhibit a preference for statistical fitting over logical reasoning. Spurious correlations might be memorized when there exists statistical bias in training data, which severely limits the model performance especially in small data scenarios. In this work, we introduce Counterfactual Adversarial Training framework (CAT) to tackle the problem from a causality perspective. Particularly, for a specific sample, CAT first generates a counterfactual representation through latent space interpolation in an adversarial manner, and then performs Counterfactual Risk Minimization (CRM) on each original-counterfactual pair to adjust sample-wise loss weight dynamically, which encourages the model to explore the true causal effect. Extensive experiments demonstrate that CAT achieves substantial performance improvement over SOTA across different downstream tasks, including sentence classification, natural language inference and question answering.- Anthology ID:
- 2021.findings-emnlp.413
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2021
- Month:
- November
- Year:
- 2021
- Address:
- Punta Cana, Dominican Republic
- Editors:
- Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
- Venue:
- Findings
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 4809–4820
- Language:
- URL:
- https://aclanthology.org/2021.findings-emnlp.413
- DOI:
- 10.18653/v1/2021.findings-emnlp.413
- Cite (ACL):
- Wei Wang, Boxin Wang, Ning Shi, Jinfeng Li, Bingyu Zhu, Xiangyu Liu, and Rong Zhang. 2021. Counterfactual Adversarial Learning with Representation Interpolation. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 4809–4820, Punta Cana, Dominican Republic. Association for Computational Linguistics.
- Cite (Informal):
- Counterfactual Adversarial Learning with Representation Interpolation (Wang et al., Findings 2021)
- PDF:
- https://preview.aclanthology.org/ingest-bitext-workshop/2021.findings-emnlp.413.pdf
- Code
- shininglab/cat
- Data
- SNLI, SQuAD, Yahoo! Answers