Preserving AUC Fairness in Learning with Noisy Protected Groups

Mingyang Wu, Li Lin, Wenbin Zhang, Xin Wang, Zhenhuan Yang, Shu Hu
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:67427-67448, 2025.

Abstract

The Area Under the ROC Curve (AUC) is a key metric for classification, especially under class imbalance, with growing research focus on optimizing AUC over accuracy in applications like medical image analysis and deepfake detection. This leads to fairness in AUC optimization becoming crucial as biases can impact protected groups. While various fairness mitigation techniques exist, fairness considerations in AUC optimization remain in their early stages, with most research focusing on improving AUC fairness under the assumption of clean protected groups. However, these studies often overlook the impact of noisy protected groups, leading to fairness violations in practice. To address this, we propose the first robust AUC fairness approach under noisy protected groups with fairness theoretical guarantees using distributionally robust optimization. Extensive experiments on tabular and image datasets show that our method outperforms state-of-the-art approaches in preserving AUC fairness. The code is in https://github.com/Purdue-M2/AUC_Fairness_with_Noisy_Groups.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-wu25q, title = {Preserving {AUC} Fairness in Learning with Noisy Protected Groups}, author = {Wu, Mingyang and Lin, Li and Zhang, Wenbin and Wang, Xin and Yang, Zhenhuan and Hu, Shu}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {67427--67448}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/wu25q/wu25q.pdf}, url = {https://proceedings.mlr.press/v267/wu25q.html}, abstract = {The Area Under the ROC Curve (AUC) is a key metric for classification, especially under class imbalance, with growing research focus on optimizing AUC over accuracy in applications like medical image analysis and deepfake detection. This leads to fairness in AUC optimization becoming crucial as biases can impact protected groups. While various fairness mitigation techniques exist, fairness considerations in AUC optimization remain in their early stages, with most research focusing on improving AUC fairness under the assumption of clean protected groups. However, these studies often overlook the impact of noisy protected groups, leading to fairness violations in practice. To address this, we propose the first robust AUC fairness approach under noisy protected groups with fairness theoretical guarantees using distributionally robust optimization. Extensive experiments on tabular and image datasets show that our method outperforms state-of-the-art approaches in preserving AUC fairness. The code is in https://github.com/Purdue-M2/AUC_Fairness_with_Noisy_Groups.} }
Endnote
%0 Conference Paper %T Preserving AUC Fairness in Learning with Noisy Protected Groups %A Mingyang Wu %A Li Lin %A Wenbin Zhang %A Xin Wang %A Zhenhuan Yang %A Shu Hu %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-wu25q %I PMLR %P 67427--67448 %U https://proceedings.mlr.press/v267/wu25q.html %V 267 %X The Area Under the ROC Curve (AUC) is a key metric for classification, especially under class imbalance, with growing research focus on optimizing AUC over accuracy in applications like medical image analysis and deepfake detection. This leads to fairness in AUC optimization becoming crucial as biases can impact protected groups. While various fairness mitigation techniques exist, fairness considerations in AUC optimization remain in their early stages, with most research focusing on improving AUC fairness under the assumption of clean protected groups. However, these studies often overlook the impact of noisy protected groups, leading to fairness violations in practice. To address this, we propose the first robust AUC fairness approach under noisy protected groups with fairness theoretical guarantees using distributionally robust optimization. Extensive experiments on tabular and image datasets show that our method outperforms state-of-the-art approaches in preserving AUC fairness. The code is in https://github.com/Purdue-M2/AUC_Fairness_with_Noisy_Groups.
APA
Wu, M., Lin, L., Zhang, W., Wang, X., Yang, Z. & Hu, S.. (2025). Preserving AUC Fairness in Learning with Noisy Protected Groups. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:67427-67448 Available from https://proceedings.mlr.press/v267/wu25q.html.

Related Material