Enhancing Model Robustness and Fairness with Causality: A Regularization Approach

Zhao Wang, Kai Shu, Aron Culotta


Abstract
Recent work has raised concerns on the risk of spurious correlations and unintended biases in statistical machine learning models that threaten model robustness and fairness. In this paper, we propose a simple and intuitive regularization approach to integrate causal knowledge during model training and build a robust and fair model by emphasizing causal features and de-emphasizing spurious features. Specifically, we first manually identify causal and spurious features with principles inspired from the counterfactual framework of causal inference. Then, we propose a regularization approach to penalize causal and spurious features separately. By adjusting the strength of the penalty for each type of feature, we build a predictive model that relies more on causal features and less on non-causal features. We conduct experiments to evaluate model robustness and fairness on three datasets with multiple metrics. Empirical results show that the new models built with causal awareness significantly improve model robustness with respect to counterfactual texts and model fairness with respect to sensitive attributes.
Anthology ID:
2021.cinlp-1.3
Volume:
Proceedings of the First Workshop on Causal Inference and NLP
Month:
November
Year:
2021
Address:
Punta Cana, Dominican Republic
Editors:
Amir Feder, Katherine Keith, Emaad Manzoor, Reid Pryzant, Dhanya Sridhar, Zach Wood-Doughty, Jacob Eisenstein, Justin Grimmer, Roi Reichart, Molly Roberts, Uri Shalit, Brandon Stewart, Victor Veitch, Diyi Yang
Venue:
CINLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
33–43
Language:
URL:
https://aclanthology.org/2021.cinlp-1.3
DOI:
10.18653/v1/2021.cinlp-1.3
Bibkey:
Cite (ACL):
Zhao Wang, Kai Shu, and Aron Culotta. 2021. Enhancing Model Robustness and Fairness with Causality: A Regularization Approach. In Proceedings of the First Workshop on Causal Inference and NLP, pages 33–43, Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Enhancing Model Robustness and Fairness with Causality: A Regularization Approach (Wang et al., CINLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.cinlp-1.3.pdf
Code
 tapilab/emnlp-2021-regularization