CDAˆ2: Counterfactual Diffusion Augmentation for Cross-Domain Adaptation in Low-Resource Sentiment Analysis

Dancheng Xin, Kaiqi Zhao, Jingyun Sun, Yang Li


Abstract
Domain adaptation is widely employed in cross-domain sentiment analysis, enabling the transfer of models from label-rich source domains to target domain with fewer or no labels. However, concerns have been raised regarding their robustness and sensitivity to data distribution shift, particularly when encountering significant disparities in data distribution between the different domains. To tackle this problem, we introduce a framework CDAˆ2 for cross-domain adaptation in low-resource sentiment analysis, which utilizes counterfactual diffusion augmentation. Specifically, it employs samples derived from domain-relevant word substitutions in source domain samples to guide the diffusion model for generating high-quality counterfactual target domain samples. We adopt a soft absorbing state and MMD loss during the training stage, and use advanced ODE solvers to expedite the sampling process. Our experiments demonstrate that CDAˆ2 generates high-quality target samples and achieves state-of-the-art performance in cross-domain sentiment analysis.
Anthology ID:
2025.coling-main.6
Volume:
Proceedings of the 31st International Conference on Computational Linguistics
Month:
January
Year:
2025
Address:
Abu Dhabi, UAE
Editors:
Owen Rambow, Leo Wanner, Marianna Apidianaki, Hend Al-Khalifa, Barbara Di Eugenio, Steven Schockaert
Venue:
COLING
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
61–72
Language:
URL:
https://aclanthology.org/2025.coling-main.6/
DOI:
Bibkey:
Cite (ACL):
Dancheng Xin, Kaiqi Zhao, Jingyun Sun, and Yang Li. 2025. CDAˆ2: Counterfactual Diffusion Augmentation for Cross-Domain Adaptation in Low-Resource Sentiment Analysis. In Proceedings of the 31st International Conference on Computational Linguistics, pages 61–72, Abu Dhabi, UAE. Association for Computational Linguistics.
Cite (Informal):
CDAˆ2: Counterfactual Diffusion Augmentation for Cross-Domain Adaptation in Low-Resource Sentiment Analysis (Xin et al., COLING 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.coling-main.6.pdf