Abstract
Fairness is increasingly becoming an important issue in machine learning. Representation learning is a popular approach recently that aims at mitigating discrimination by generating representation on the historical data so that further predictive analysis conducted on the representation is fair. Inspired by this approach, we propose a novel structure, called GIFair, for generating a representation that can simultaneously reconcile utility with both group and individual fairness, compared with most relevant studies that only focus on group fairness. Due to the conflict of the two fairness targets, we need to trade group fairness off against individual fairness in addition to considering the utility of classifiers. To achieve an optimized trade-off performance, we include a focal loss function so that all the targets can receive more balanced attention. Experiments conducted on three real datasets show that GIFair can achieve a better utility-fairness trade-off compared with existing models.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Zehlike, M., Bonchi, F., Castillo, C., Hajian, S., Megahed, M., Baeza-Yates, R.: Fa*ir: a fair top-k ranking algorithm. In: CIKM, pp. 1569–1578 (2017)
Hardt, M., Price, E., Srebro, N.: Equality of opportunity in supervised learning. In: NeurIPS, pp. 3323–3331 (2016)
Kamiran, F., Calders, T.: Data preprocessing techniques for classification without discrimination. In: KAIS, vol. 33, pp. 1–33 (2011)
Dwork, C., Hardt, M., Pitassi, T., Reingold, O., Zemel, R.: Fairness through awareness. In: ITCS, pp. 214–226 (2012)
Kusner, M.J., Loftus, J., Russell, C., Silva, R.: Counterfactual fairness. In: Advances in Neural Information Processing Systems, vol. 30 (2017)
Salimi, B., Rodriguez, L., Howe, B., Suciu, D.: Interventional fairness: causal database repair for algorithmic fairness. In: SIGMOD, pp. 793–810 (2019)
Zemel, R., Wu, Y., Swersky, K., Pitassi, T., Dwork, C.: Learning fair representations. In: ICML, vol. 28, no. 3, pp. 325–333 (2013)
Edwards, H., Storkey, A.: Censoring representations with an adversary. In: ICLR (2016)
Zhao, H., Coston, A., Adel, T., Gordon, G.J.: Conditional learning of fair representations. In: ICLR (2020)
Han, S., et al.: Dualfair: fair representation learning at both group and individual levels via contrastive self-supervision, arXiv preprint arXiv:2303.08403 (2023)
Binns, R.: On the apparent conflict between individual and group fairness. In: Proceedings of the Conference on Fairness, Accountability, and Transparency (2020)
Lahoti, P., Gummadi, K.P., Weikum, G.: ifair: learning individually fair data representations for algorithmic decision making. In: ICDE, pp. 1334–1345 (2019)
Madras, D., Creager, E., Pitassi, T., Zemel, R.: Learning adversarially fair and transferable representations. In: ICML, vol. 80, pp. 3384–3393 (2018)
Kim, D., Kim, K., Kong, I., Ohn, I., Kim, Y.: Learning fair representation with a parametric integral probability metric, arXiv preprint arXiv:2202.02943 (2022)
Goodfellow, I.J., et al.: Generative adversarial nets. In: NeurIPS (2014)
Liu, H., Wong, R.C.-W.: Adversarial learning of group and individual fair representations (supplementary material) (2024). https://github.com/satansin/GIFair
Saxena, D., Cao, J.: Generative adversarial networks (GANs) challenges, solutions, and future directions. ACM Comput. Surv. 54(3), 1–42 (2021)
Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen, X.: Improved techniques for training GANs. In: Advances in Neural Information Processing Systems, vol. 29 (2016)
Lin, T.-Y., Goyal, P., Girshick, R.B., He, K., Dollár, P.: Focal loss for dense object detection. In: ICCV, pp. 2999–3007 (2017)
Angwin, J., Larson, J., Mattu, S., Kirchner, L.: Machine bias: risk assessments in criminal sentencing. ProPublica (2016). https://www.propublica.org/article/machine-bias-risk-assessments-in-criminal-sentencing
Becker, B., Kohavi, R.: Adult. UCI Machine Learning Repository (1996). https://doi.org/10.24432/C5XW20
Hofmann, H.: Statlog (German Credit Data). UCI Machine Learning Repository (1994). https://doi.org/10.24432/C5NC77
Acknowledgements
We greatly thank Zheng Zhang for his contribution on this paper.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Liu, H., Wong, R.CW. (2024). Adversarial Learning of Group and Individual Fair Representations. In: Yang, DN., Xie, X., Tseng, V.S., Pei, J., Huang, JW., Lin, J.CW. (eds) Advances in Knowledge Discovery and Data Mining. PAKDD 2024. Lecture Notes in Computer Science(), vol 14645. Springer, Singapore. https://doi.org/10.1007/978-981-97-2242-6_15
Download citation
DOI: https://doi.org/10.1007/978-981-97-2242-6_15
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-97-2241-9
Online ISBN: 978-981-97-2242-6
eBook Packages: Computer ScienceComputer Science (R0)