Chasing Fairness Under Distribution Shift: A Model Weight Perturbation Approach
Fairness in machine learning has attracted increasing attention in recent years. The fairness methods improving algorithmic fairness for in-distribution data may not perform well under distribution shifts. In this paper, we first theoretically demonstrate the inherent connection between distribution shift, data perturbation, and model weight perturbation. Subsequently, we analyze the sufficient conditions to guarantee fairness (i.e., low demographic parity) for the target dataset, including fairness for the source dataset, and low prediction difference between the source and target datasets for each sensitive attribute group. Motivated by these sufficient conditions, we propose robust fairness regularization (RFR) by considering the worst case within the model weight perturbation ball for each sensitive attribute group. We evaluate the effectiveness of our proposed RFR algorithm on synthetic and real distribution shifts across various datasets. Experimental results demonstrate that RFR achieves better fairness-accuracy trade-off performance compared with several baselines. The source code is available at \url{https://github.com/zhimengj0326/RFR_NeurIPS23}.
Code (1)
Tasks
AttributeFairnessSimilar Papers 제목 키워드 기반
Fix Representation (Optimally) Before Fairness: Finite-Sample Shrinkage Population Correction and the True Price of Fairness Under Subpopulation Shift
Machine learning practitioners frequently observe tension between predictive accuracy and group fairness constraints -- yet sometimes fairness interventions appear to improve accuracy. We show that both phenomena can be …
How Robust is Your Fairness? Evaluating and Sustaining Fairness under Unseen Distribution Shifts
Increasing concerns have been raised on deep learning fairness in recent years. Existing fairness-aware machine learning methods mainly focus on the fairness of in-distribution data. However, in real-world applications, …
FairnessTransferring Fairness under Distribution Shifts via Fair Consistency Regularization
The increasing reliance on ML models in high-stakes tasks has raised a major concern on fairness violations. Although there has been a surge of work that improves algorithmic fairness, most of them are under the assumpti…
FairnessFairness under Covariate Shift: Improving Fairness-Accuracy tradeoff with few Unlabeled Test Samples
Covariate shift in the test data is a common practical phenomena that can significantly downgrade both the accuracy and the fairness performance of the model. Ensuring fairness across different sensitive groups under cov…
FairnessOut-of-Distribution GeneralizationDomain Adaptation meets Individual Fairness. And they get along
Many instances of algorithmic bias are caused by distributional shifts. For example, machine learning (ML) models often perform worse on demographic groups that are underrepresented in the training data. In this paper, w…
Domain AdaptationFairness