Fair Classification Without Sensitive Attribute Labels via Dynamic Reweighting
Source abstract
Abstract
Fairness-aware classification with respect to sensitive attributes, such as gender and race, is one of the most important topics in machine learning. Although numerous studies have made outstanding progress through various approaches, one key limitation is that they necessarily require additional labels of sensitive attributes for training. This poses a significant challenge since sensitive attributes typically correspond to personal information. To this end, we propose a novel reweighting method that dynamically gives more weights to underrepresented groups across potential sensitive attributes. Without auxiliary networks or strong assumptions about sensitive attributes, the proposed method significantly improves fairness under various scenarios on benchmark datasets, outperforming the existing state-of-the-art methods.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Ethics and Social Impacts of AI · Adversarial Robustness in Machine Learning · Explainable Artificial Intelligence (XAI)
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Artificial Intelligence, Inha University, Incheon 22212, Republic of Korea
Department of Computer Science and Engineering, Incheon National University, Incheon 22012, Republic of Korea
Funding
Incheon National University Research Grant
References (60)
Show source-provided references
1. ImageNet Large Scale Visual Recognition Challenge10.1007/s11263-015-0816-y ↗
2. Liu, Z., Luo, P., Wang, X., and Tang, X. (2015). Deep Learning Face Attributes in the Wild. Proceedings of International Conference on Computer Vision (ICCV), IEEE.10.1109/ICCV.2015.425 ↗
3. He, K., Zhang, X., Ren, S., and Sun, J. (2016). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE.10.1109/CVPR.2016.90 ↗
4. Karras, T., Aila, T., Laine, S., and Lehtinen, J. (May, January 30). Progressive Growing of GANs for Improved Quality, Stability, and Variation. Proceedings of the International Conference on Learning Representations, Vancouver, BC, Canada.
5. Brandao, M. (2019). Age and gender bias in pedestrian detection algorithms. arXiv.
6. Kärkkäinen, K., and Joo, J. (2019). FairFace: Face Attribute Dataset for Balanced Race, Gender, and Age. arXiv.
7. Burns, K., Hendricks, L.A., Darrell, T., and Rohrbach, A. (2018). Women also Snowboard: Overcoming Bias in Captioning Models. Proceedings of the European Conference on Computer Vision (ECCV), IEEE.10.1007/978-3-030-01219-9_47 ↗
8. Angwin, J., Larson, J., Mattu, S., and Kirchner, L. (ProPublica, 2016). Machine bias: There’s software used across the country to predict future criminals. And it’s biased against blacks, ProPublica.
9. Dougherty, C. (Twitter, 2015). Google photos mistakenly labels black people gorillas, Twitter.
10. Lomas, N. (TechCrunch, 2017). FaceApp apologizes for building a racist AI, TechCrunch.
11. Dwork, C., Hardt, M., Pitassi, T., Reingold, O., and Zemel, R. (2012). Fairness through Awareness. ITCS ’12: Proceedings of the 3rd Innovations in Theoretical Computer Science Conference, ACM.10.1145/2090236.2090255 ↗
12. Guyon, I., Luxburg, U.V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., and Garnett, R. (2017). Counterfactual Fairness. Proceedings of the Advances in Neural Information Processing Systems 30, Curran Associates, Inc.
13. Wang, T., Zhao, J., Yatskar, M., Chang, K.W., and Ordonez, V. (2019). Balanced Datasets Are Not Enough: Estimating and Mitigating Gender Bias in Deep Image Representations. 2019 IEEE/CVF International Conference on Computer Vision (ICCV), IEEE.10.1109/ICCV.2019.00541 ↗
14. Wang, Z., Qinami, K., Karakozis, I.C., Genova, K., Nair, P., Hata, K., and Russakovsky, O. Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigation. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
15. Gong, S., Liu, X., and Jain, A. (2020). Jointly De-biasing Face Recognition and Demographic Attribute Estimation. Computer Vision—ECCV 2020, Springer.10.1007/978-3-030-58526-6_20 ↗
16. Hardt, M., Price, E., and Srebro, N. (2016). Equality of Opportunity in Supervised Learning. NIPS’16: Proceedings of the 30th International Conference on Neural Information Processing Systems, ACM.
17. Ramaswamy, V.V., Kim, S.S.Y., and Russakovsky, O. (2021). Fair Attribute Classification Through Latent Space De-Biasing. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.10.1109/CVPR46437.2021.00918 ↗
18. Fairness GAN: Generating datasets with fairness properties using a generative adversarial network10.1147/JRD.2019.2945519 ↗
19. Xu, D., Yuan, S., Zhang, L., and Wu, X. (2018). FairGAN: Fairness-aware Generative Adversarial Networks. 2018 IEEE International Conference on Big Data (Big Data), IEEE.10.1109/BigData.2018.8622525 ↗
20. Creager, E., Madras, D., Jacobsen, J.H., Weis, M., Swersky, K., Pitassi, T., and Zemel, R. (2019, January 9–15). Flexibly Fair Representation Learning by Disentanglement. Proceedings of the 36th International Conference on Machine Learning, Long Beach, CA, USA.
21. Park, S., Hwang, S., Kim, D., and Byun, H. (2021, January 2–9). Learning Disentangled Representation for Fair Facial Attribute Classification via Fairness-awareunbiased Information Alignment. Proceedings of the AAAI Conference on Artificial Intelligence, Virtual.10.1609/aaai.v35i3.16341 ↗
22. Kim, B., Kim, H., Kim, K., Kim, S., and Kim, J. (2019). Learning Not to Learn: Training Deep Neural Networks With Biased Data. Proceedings of the The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.10.1109/CVPR.2019.00922 ↗
23. Park, S., Lee, J., Lee, P., Hwang, S., Kim, D., and Byun, H. (2022). Fair Contrastive Learning for Facial Attribute Classification. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.10.1109/CVPR52688.2022.01014 ↗
24. Sagawa, S., Koh, P.W., Hashimoto, T.B., and Liang, P. (2020, January 30). Distributionally Robust Neural Networks. Proceedings of the International Conference on Learning Representations, Addis Ababa, Ethiopia.
25. Fair classification by loss balancing via fairness-aware batch sampling
26. Jung, S.W., Chun, S., and Moon, T. Learning Fair Classifiers with Partially Annotated Group Labels. 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).10.1109/CVPR52688.2022.01010 ↗
27. Seo, S., Lee, J.Y., and Han, B. (2022). Unsupervised Learning of Debiased Representations With Pseudo-Attributes. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.10.1109/CVPR52688.2022.01624 ↗
28. Fleet, D., Pajdla, T., Schiele, B., and Tuytelaars, T. (2014). Microsoft COCO: Common Objects in Context. Proceedings of the Computer Vision—ECCV 2014, Springer.10.1007/978-3-319-10590-1 ↗
29. Heilbron, F.C., Escorcia, V., Ghanem, B., and Niebles, J.C. (2015). ActivityNet: A large-scale video benchmark for human activity understanding. Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.10.1109/CVPR.2015.7298698 ↗
30. Wang, H., He, Z., Lipton, Z.L., and Xing, E.P. (2019, January 6–9). Learning Robust Representations by Projecting Superficial Statistics Out. Proceedings of the International Conference on Learning Representations, New Orleans, LA, USA.
31. Bahng, H., Chun, S., Yun, S., Choo, J., and Oh, S.J. (2020). Learning De-biased Representations with Biased Representations. Proceedings of the 37th International Conference on Machine Learning, PMLR.
32. Beygelzimer, A., Dauphin, Y., Liang, P., and Vaughan, J.W. (2021). Unbiased Classification through Bias-Contrastive and Bias-Balanced Learning. Proceedings of the Advances in Neural Information Processing Systems, Curran Associates, Inc.
33. Learning from Failure: De-biasing Classifier from Biased Classifier
34. Beygelzimer, A., Dauphin, Y., Liang, P., and Vaughan, J.W. (2021). Learning Debiased Representation via Disentangled Feature Augmentation. Proceedings of the Advances in Neural Information Processing Systems, Curran Associates, Inc.
35. Lim, J., Kim, Y., Kim, B., Ahn, C., Shin, J., Yang, E., and Han, S. (2023). BiasAdv: Bias-Adversarial Augmentation for Model Debiasing. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.10.1109/CVPR52729.2023.00373 ↗
36. Zhang, Y.K., Wang, Q.W., Zhan, D.C., and Ye, H.J. (2023). Learning Debiased Representations via Conditional Attribute Interpolation. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.10.1109/CVPR52729.2023.00734 ↗
37. Raedt, L.D. (2023). Fairness without the Sensitive Attribute via Causal Variational Autoencoder. Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI-22, Vienna, Austria, 23–29 July 2022, IJCAI.
38. Zhao, T., Dai, E., Shu, K., and Wang, S. (2022). Towards Fair Classifiers Without Sensitive Attributes: Exploring Biases in Related Features. WSDM ’22: Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining, ACM.10.1145/3488560.3498493 ↗
39. Hashimoto, T., Srivastava, M., Namkoong, H., and Liang, P. (2018). Fairness Without Demographics in Repeated Loss Minimization. International Conference on Machine Learning, PMLR.
40. Lahoti, P., Beutel, A., Chen, J., Lee, K., Prost, F., Thain, N., Wang, X., and Chi, E.H. (2020). Fairness without Demographics through Adversarially Reweighted Learning. Advances in Neural Information Processing Systems; NIPS’20, Curran Associates, Inc.
41. Liu, E.Z., Haghgoo, B., Chen, A.S., Raghunathan, A., Koh, P.W., Sagawa, S., Liang, P., and Finn, C. (2021). Just Train Twice: Improving Group Robustness without Training Group Information. arXiv.
42. Chai, J., Jang, T., and Wang, X. (2022). Fairness without Demographics through Knowledge Distillation. Proceedings of the Advances in Neural Information Processing Systems, Curran Associates, Inc.
43. Fairness with Adaptive Weights
44. Data Pre-Processing Techniques for Classification without Discrimination10.1007/s10115-011-0463-8 ↗
45. Zhang, Z., Song, Y., and Qi, H. (2017). Age Progression/Regression by Conditional Adversarial Autoencoder. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.10.1109/CVPR.2017.463 ↗
46. Raff, E., and Sylvester, J. (2018). Gradient Reversal against Discrimination: A Fair Neural Network Learning Approach. Proceedings of the 2018 IEEE 5th International Conference on Data Science and Advanced Analytics (DSAA), IEEE.10.1109/DSAA.2018.00029 ↗
47. Sarhan, M.H., Navab, N., Eslami, A., and Albarqouni, S. (2020, January 23–28). Fairness by Learning Orthogonal Disentangled Representations. Proceedings of the Computer Vision—ECCV 2020—16th European Conference, Glasgow, UK.10.1007/978-3-030-58526-6_44 ↗
48. Zhang, B.H., Lemoine, B., and Mitchell, M. (2018). Mitigating Unwanted Biases with Adversarial Learning. AIES ’18: Proceedings of the Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society, ACM.10.1145/3278721.3278779 ↗
49. Wadsworth, C., Vera, F., and Piech, C. (2018). Achieving fairness through adversarial learning: An application to recidivism prediction. arXiv.
50. Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y. (2014). Generative adversarial nets. Advances in Neural Information Processing Systems, Curran Associates, Inc.
51. Lokhande, V.S., Sohn, K., Yoon, J., Udell, M., Lee, C.Y., and Pfister, T. (2022, January 22). Towards Group Robustness in the Presence of Partial Group Labels. Proceedings of the ICML 2022: Workshop on Spurious Correlations, Invariance and Stability, Baltimore, MD, USA.
52. Chai, J., and Wang, X. (2022). Self-Supervised Fair Representation Learning without Demographics. Advances in Neural Information Processing Systems, Curran Associates, Inc.
53. Jang, T., and Wang, X. (2023). Difficulty-Based Sampling for Debiased Contrastive Representation Learning. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.10.1109/CVPR52729.2023.02302 ↗
54. Fairness without Demographics through Shared Latent Space-Based Debiasing
55. Towards Harmless Rawlsian Fairness Regardless of Demographic Prior
56. Luo, Y., Li, Z., Liu, Q., and Zhu, J. (2025, January 3–7). Fairness without Demographics through Learning Graph of Gradients. Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining, V.1, KDD 2025, Toronto, ON, Canada.10.1145/3690624.3709160 ↗
57. Lin, T., Goyal, P., Girshick, R.B., He, K., and Dollár, P. (2017). Focal Loss for Dense Object Detection. arXiv.10.1109/ICCV.2017.324 ↗
58. Jordan, M., Kearns, M., and Solla, S. (1997). Training Methods for Adaptive Boosting of Neural Networks. Advances in Neural Information Processing Systems, MIT Press.
59. Badirli, S., Liu, X., Xing, Z., Bhowmik, A., Doan, K.D., and Keerthi, S. (2020). Gradient Boosting Neural Networks: GrowNet. arXiv.
60. Kingma, D.P., and Ba, J. (2015, January 7–9). Adam: A Method for Stochastic Optimization. Proceedings of the 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA.