Abstract
Much research has been devoted to the problem of learning fair representations; however, they do not explicitly state the relationship between latent representations. In many real-world applications, there may be causal relationships between latent representations. Furthermore, most fair representation learning methods focus on group-level fairness and are based on correlation, ignoring the causal relationships underlying the data. In this work, we theoretically demonstrate that using the structured representations enables downstream predictive models to achieve counterfactual fairness, and then we propose the Counterfactual Fairness Variational AutoEncoder (CF-VAE) to obtain structured representations with respect to domain knowledge. The experimental results show that the proposed method achieves better fairness and accuracy performance than the benchmark fairness methods.
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
Similar content being viewed by others
References
Brennan, T., Dieterich, W., Ehret, B.: Evaluating the predictive validity of the compass risk and needs assessment system. Crim. Just. Behav. 36(1), 21–40 (2009)
Calmon, F.P., Wei, D., Vinzamuri, B., Ramamurthy, K.N., Varshney, K.R.: Optimized pre-processing for discrimination prevention. In: NeurIPS, pp. 3992–4001 (2017)
Cheng, D., Li, J., Liu, L., Yu, K., Le, T.D., Liu, J.: Toward unique and unbiased causal effect estimation from data with hidden variables. IEEE Trans. Neural Netw. Learn. Syst., 1–13 (2022)
Chiappa, S.: Path-specific counterfactual fairness. In: AAAI, pp. 7801–7808 (2019)
Coşer, A., Maer-matei, M.M., Albu, C.: Predictive models for loan default risk assessment. Econ. Comput. Econ. Cybern. Stud. Res. 53(2), 149–165 (2019)
Creager, E., et al.: Flexibly fair representation learning by disentanglement. In: ICML, pp. 1436–1445 (2019)
Dua, D., Graff, C.: UCI machine learning repository (2017)
Dwork, C., Hardt, M., Pitassi, T., Reingold, O., Zemel, R.S.: Fairness through awareness. In: ITCS, pp. 214–226 (2012)
Feldman, M., Friedler, S.A., Moeller, J., Scheidegger, C., Venkatasubramanian, S.: Certifying and removing disparate impact. In: SIGKDD, pp. 259–268 (2015)
Gitiaux, X., Rangwala, H.: Learning smooth and fair representations. In: AISTATS, pp. 253–261 (2021)
Hardt, M., Price, E., Srebro, N.: Equality of opportunity in supervised learning. In: NeurIPS, pp. 3315–3323 (2016)
Higgins, I., et al.: beta-vae: learning basic visual concepts with a constrained variational framework. In: ICLR, pp. 1–22 (2017)
Kamiran, F., Calders, T.: Data preprocessing techniques for classification without discrimination. Knowl. Inf. Syst. 33(1), 1–33 (2012)
Kim, S., Joshi, P., Kalsi, P.S., Taheri, P.: Crime analysis through machine learning. In: IEMCON, pp. 415–420 (2018)
Kingma, D.P., Welling, M.: Auto-encoding variational bayes. In: ICLR, pp. 1–14 (2014)
Kruppa, J., Schwarz, A., Arminger, G., Ziegler, A.: Consumer credit risk: individual probability estimates using machine learning. Expert Syst. Appl. 40(13), 5125–5131 (2013)
Kusner, M.J., Loftus, J.R., Russell, C., Silva, R.: Counterfactual fairness. In: NeurIPS, pp. 4066–4076 (2017)
Lewis, D.: Counterfactuals. John Wiley & Sons, Hoboken (2013)
Li, J., Liu, J., Liu, L., Le, T.D., Ma, S., Han, Y.: Discrimination detection by causal effect estimation. In: IEEE BigData, pp. 1087–1094 (2017)
Louizos, C., Swersky, K., Li, Y., Welling, M., Zemel, R.S.: The variational fair autoencoder. In: ICLR, pp. 1–11 (2016)
Mac, R.: Facebook apologizes after ai puts ‘primates’ label on video of black men (2021). https://www.nytimes.com/2021/09/03/technology/facebook-ai-race-primates.html
Madras, D., Creager, E., Pitassi, T., Zemel, R.S.: Fairness through causal awareness: learning causal latent-variable models for biased data. In: FAT*, pp. 349–358 (2019)
Mehrabi, N., Morstatter, F., Saxena, N., Lerman, K., Galstyan, A.: A survey on bias and fairness in machine learning. ACM Comput. Surv. 54(6), 115:1–115:35 (2021)
Nabi, R., Shpitser, I.: Fair inference on outcomes. In: AAAI, pp. 1931–1940 (2018)
Park, S., Hwang, S., Kim, D., Byun, H.: Learning disentangled representation for fair facial attribute classification via fairness-aware information alignment. In: AAAI, pp. 2403–2411 (2021)
Pearl, J.: Causality. Cambridge University Press, Cambridge (2009)
Spirtes, P., Glymour, C.N., Scheines, R., Heckerman, D.: Causation, Prediction, and Search. MIT press, Cambridge (2000)
Wightman, L.F.: Lsac national longitudinal bar passage study. lsac research report series (1998)
Xie, P., Wu, W., Zhu, Y., Xing, E.P.: Orthogonality-promoting distance metric learning: convex relaxation and theoretical analysis. In: ICML, pp. 5399–5408 (2018)
Zafar, M.B., Valera, I., Gomez-Rodriguez, M., Gummadi, K.P.: Fairness beyond disparate treatment & disparate impact: Learning classification without disparate mistreatment. In: WWW, pp. 1171–1180 (2017)
Zemel, R.S., Wu, Y., Swersky, K., Pitassi, T., Dwork, C.: Learning fair representations. In: ICML, pp. 325–333 (2013)
Zhang, L., Wu, X.: Anti-discrimination learning: a causal modeling-based framework. Int. J. Data Sci. Anal. 4(1), 1–16 (2017)
Zhang, L., Wu, Y., Wu, X.: A causal framework for discovering and removing direct and indirect discrimination. In: IJCAI, pp. 3929–3935 (2017)
Acknowledgements
This work has received partial support from the Australian Research Council Discovery Project (DP200101210) to J. Li, J. Liu and K. Wang, the discovery grant from the Natural Sciences and Engineering Research Council of Canada to K. Wang, and the University Presidents Scholarship (UPS) of the University of South Australia to Z. Xu.
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Xu, Z., Liu, J., Cheng, D., Li, J., Liu, L., Wang, K. (2023). Disentangled Representation with Causal Constraints for Counterfactual Fairness. In: Kashima, H., Ide, T., Peng, WC. (eds) Advances in Knowledge Discovery and Data Mining. PAKDD 2023. Lecture Notes in Computer Science(), vol 13935. Springer, Cham. https://doi.org/10.1007/978-3-031-33374-3_37
Download citation
DOI: https://doi.org/10.1007/978-3-031-33374-3_37
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-33373-6
Online ISBN: 978-3-031-33374-3
eBook Packages: Computer ScienceComputer Science (R0)