Abstract
Fair representation learning transforms user data into a representation that ensures fairness and utility regardless of the downstream application. However, learning individually fair representations, i.e., guaranteeing that similar individuals are treated similarly, remains challenging in high-dimensional settings such as computer vision. In this work, we introduce LASSI, the first representation learning method for certifying individual fairness of high-dimensional data. Our key insight is to leverage recent advances in generative modeling to capture the set of similar individuals in the generative latent space. This enables us to learn individually fair representations that map similar individuals close together by using adversarial training to minimize the distance between their representations. Finally, we employ randomized smoothing to provably map similar individuals close together, in turn ensuring that local robustness verification of the downstream application results in end-to-end fairness certification. Our experimental evaluation on challenging real-world image data demonstrates that our method increases certified individual fairness by up to 90% without significantly affecting task utility.
A. Ruoss—Work partially done while the author was at ETH Zurich.
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
Albarghouthi, A., D’Antoni, L., Drews, S., Nori, A.V.: Fairsquare: probabilistic verification of program fairness. In: Proceedings of ACM Programming Language (2017)
Balakrishnan, G., Xiong, Y., Xia, W., Perona, P.: Towards causal benchmarking of biasin face analysis algorithms. In: Ratha, N.K., Patel, V.M., Chellappa, R. (eds.) Deep Learning-Based Face Analytics. ACVPR, pp. 327–359. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-74697-1_15
Balunovic, M., Ruoss, A., Vechev, M.: Fair normalizing flows. In: International Conference on Learning Representations (2022). https://openreview.net/forum?id=BrFIKuxrZE
Bastani, O., Zhang, X., Solar-Lezama, A.: Probabilistic verification of fairness properties via concentration. In: Proceedings of ACM Programming Language (2019)
Bolukbasi, T., Chang, K., Zou, J.Y., Saligrama, V., Kalai, A.T.: Man is to computer programmer as woman is to homemaker? debiasing word embeddings. Adv. Neural Inf. Process. Syst. 29 (2016)
Brennan, T., Dieterich, W., Ehret, B.: Evaluating the predictive validity of the compas risk and needs assessment system. Crim. Just. Behav. 36, 21–40 (2009)
Buolamwini, J., Gebru, T.: Gender shades: intersectional accuracy disparities in commercial gender classification. In: Conference on Fairness, Accountability and Transparency (2018)
Burgess, C., Kim, H.: 3d shapes dataset (2018). https://github.com/deepmind/3dshapes-dataset/
Choi, Y., Dang, M., den Broeck, G.V.: Group fairness by probabilistic modeling with latent fair decisions. In: Thirty-Fifth AAAI Conference on Artificial Intelligence (2021)
Cohen, J.M., Rosenfeld, E., Kolter, J.Z.: Certified adversarial robustness via randomized smoothing. In: Proceedings of the 36th International Conference on Machine Learning (2019)
Creager, E., Met al.: Flexibly fair representation learning by disentanglement. In: Proceedings of the 36th International Conference on Machine Learning (2019)
Dash, S., Sharma, A.: Evaluating and mitigating bias in image classifiers: a causal perspective using counterfactuals. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 915–924 (2022)
Denton, E., Hutchinson, B., Mitchell, M., Gebru, T.: Detecting bias with generative counterfactual face attribute augmentation. CoRR (2019)
Dwork, C., Hardt, M., Pitassi, T., Reingold, O., Zemel, R.S.: Fairness through awareness. In: Innovations in Theoretical Computer Science (2012)
Edwards, H., Storkey, A.J.: Censoring representations with an adversary. In: 4th International Conference on Learning Representations (2016)
Ehlers, R.: Formal verification of piece-wise linear feed-forward neural networks. In: Automated Technology for Verification and Analysis - 15th International Symposium (2017)
Engstrom, L., Tran, B., Tsipras, D., Schmidt, L., Madry, A.: Exploring the landscape of spatial robustness. In: Proceedings of the 36th International Conference on Machine Learning (2019)
EU: Ethics guidelines for trustworthy AI (2019)
EU: Proposal for a regulation of the European parliament and of the council laying down harmonised rules on artificial intelligence (artificial intelligence act) and amending certain union legislative acts (2021)
Feng, R., Yang, Y., Lyu, Y., Tan, C., Sun, Y., Wang, C.: Learning fair representations via an adversarial framework. CoRR (2019)
Fleisher, W.: What’s fair about individual fairness? In: AAAI/ACM Conference on AI, Ethics, and Society, Virtual Event (2021)
FTC: Using artificial intelligence and algorithms (2020)
FTC: Aiming for truth, fairness, and equity in your company’s use of AI (2021)
Gitiaux, X., Rangwala, H.: Learning smooth and fair representations. In: The 24th International Conference on Artificial Intelligence and Statistics (2021)
Goodfellow, I.J., et al.: Generative adversarial nets. Adv. Neural Inf. Process. Syst. 27 (2014)
Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. In: 3rd International Conference on Learning Representations (2015)
Gowal, S., et al.: Achieving robustness in the wild via adversarial mixing with disentangled representations. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (2020)
Hardt, M., Price, E., Srebro, N.: Equality of opportunity in supervised learning. Adv. Neural Inf. Process. Syst. 29 (2016)
Hendricks, L.A., Burns, K., Saenko, K., Darrell, T., Rohrbach, A.: Women also snowboard: overcoming bias in captioning models. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11207, pp. 793–811. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01219-9_47
Higgins, I., et al.: beta-vae: learning basic visual concepts with a constrained variational framework. In: 5th International Conference on Learning Representations (2017)
Ilvento, C.: Metric learning for individual fairness. In: 1st Symposium on Foundations of Responsible Computing (2020)
John, P.G., Vijaykeerthy, D., Saha, D.: Verifying individual fairness in machine learning models. In: Proceedings of the Thirty-Sixth Conference on Uncertainty in Artificial Intelligence (2020)
Joo, J., Kärkkäinen, K.: Gender slopes: counterfactual fairness for computer vision models by attribute manipulation. In: Proceedings of the 2nd International Workshop on Fairness, Accountability, Transparency and Ethics in Multimedia, FATE/MM ’20, pp. 1–5. Association for Computing Machinery, New York (2020). https://doi.org/10.1145/3422841.3423533
Kärkkäinen, K., Joo, J.: Fairface: face attribute dataset for balanced race, gender, and age for bias measurement and mitigation. In: IEEE Winter Conference on Applications of Computer Vision (2021)
Karras, T., Aila, T., Laine, S., Lehtinen, J.: Progressive growing of gans for improved quality, stability, and variation. In: 6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, 30 April–3 May 2018, Conference Track Proceedings. OpenReview.net (2018). https://openreview.net/forum?id=Hk99zCeAb
Kearns, M.J., Neel, S., Roth, A., Wu, Z.S.: Preventing fairness gerrymandering: auditing and learning for subgroup fairness. In: Proceedings of the 35th International Conference on Machine Learning (2018)
Kehrenberg, T., Bartlett, M., Thomas, O., Quadrianto, N.: Null-sampling for interpretable and fair representations. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12371, pp. 565–580. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58574-7_34
Khandani, A.E., Kim, A.J., Lo, A.W.: Consumer credit-risk models via machine-learning algorithms. J. Bank. Finan. 34, 2767–2787 (2010)
Kim, B., et al.: Interpretability beyond feature attribution: quantitative testing with concept activation vectors (TCAV). In: Proceedings of the 35th International Conference on Machine Learning (2018)
Kim, H., et al.: Counterfactual fairness with disentangled causal effect variational autoencoder. In: Thirty-Fifth AAAI Conference on Artificial Intelligence (2021)
Kingma, D.P., Dhariwal, P.: Glow: generative flow with invertible 1\(\times \)1 convolutions. Adv. Neural Inf. Process. Syst. 31 (2018)
Kingma, D.P., Welling, M.: Auto-encoding variational bayes. In: 2nd International Conference on Learning Representations (2014)
Klare, B., Burge, M.J., Klontz, J.C., Bruegge, R.W.V., Jain, A.K.: Face recognition performance: role of demographic information. IEEE Trans. Inf. Forensics Secur. (2012)
Kumar, A., Goldstein, T.: Center smoothing: certified robustness for networks with structured outputs. Adv. Neural Inf. Process. Syst. 34 (2021)
Lahoti, P., Gummadi, K.P., Weikum, G.: ifair: learning individually fair data representations for algorithmic decision making. In: 35th IEEE International Conference on Data Engineering (2019)
Lahoti, P., Gummadi, K.P., Weikum, G.: Operationalizing individual fairness with pairwise fair representations. In: Proceedings of VLDB Endowment (2019)
Lang, O., et al.: Explaining in style: training a gan to explain a classifier in stylespace. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pp. 693–702 (2021)
Li, Z., Xu, C.: Discover the unknown biased attribute of an image classifier. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pp. 14970–14979 (2021)
Liang, P.P., Wu, C., Morency, L., Salakhutdinov, R.: Towards understanding and mitigating social biases in language models. In: Proceedings of the 38th International Conference on Machine Learning (2021)
Liao, J., Huang, C., Kairouz, P., Sankar, L.: Learning generative adversarial representations (GAP) under fairness and censoring constraints. CoRR (2019)
Lin, X., Zhen, H., Li, Z., Zhang, Q., Kwong, S.: Pareto multi-task learning. Adv. Neural Inf. Process. Syst. 32 (2019)
Liu, Z., Luo, P., Wang, X., Tang, X.: Deep learning face attributes in the wild. In: IEEE International Conference on Computer Vision (2015)
Locatello, F., Abbati, G., Rainforth, T., Bauer, S., Schölkopf, B., Bachem, O.: On the fairness of disentangled representations. Adv. Neural Inf. Process. Syst. 32 (2019)
Louizos, C., Swersky, K., Li, Y., Welling, M., Zemel, R.S.: The variational fair autoencoder. In: 4th International Conference on Learning Representations (2016)
Madras, D., Creager, E., Pitassi, T., Zemel, R.S.: Learning adversarially fair and transferable representations. In: Proceedings of the 35th International Conference on Machine Learning (2018)
Madry, A., Makelov, A., Schmidt, L., Tsipras, D., Vladu, A.: Towards deep learning models resistant to adversarial attacks. In: 6th International Conference on Learning Representations (2018)
Maity, S., Xue, S., Yurochkin, M., Sun, Y.: Statistical inference for individual fairness. In: 9th International Conference on Learning Representations (2021)
Martínez, N., Bertrán, M., Sapiro, G.: Minimax pareto fairness: a multi objective perspective. In: Proceedings of the 37th International Conference on Machine Learning (2020)
McDuff, D.J., Cheng, R., Kapoor, A.: Identifying bias in AI using simulation. CoRR (2018)
McNamara, D., Ong, C.S., Williamson, R.C.: Costs and benefits of fair representation learning. In: Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society (2019)
Mirman, M., Hägele, A., Bielik, P., Gehr, T., Vechev, M.T.: Robustness certification with generative models. In: 42nd ACM SIGPLAN International Conference on Programming Language Design and Implementation (2021)
Mukherjee, D., Yurochkin, M., Banerjee, M., Sun, Y.: Two simple ways to learn individual fairness metrics from data. In: Proceedings of the 37th International Conference on Machine Learning (2020)
Oneto, L., Donini, M., Pontil, M., Maurer, A.: Learning fair and transferable representations with theoretical guarantees. In: 7th IEEE International Conference on Data Science and Advanced Analytics (2020)
Park, J.H., Shin, J., Fung, P.: Reducing gender bias in abusive language detection. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (2018)
Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library. In: Wallach, H.M., Larochelle, H., Beygelzimer, A., d’Alché-Buc, F., Fox, E.B., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 32 (2019)
Raji, I.D., Buolamwini, J.: Actionable auditing: investigating the impact of publicly naming biased performance results of commercial AI products. In: Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society (2019)
Ramaswamy, V.V., Kim, S.S.Y., Russakovsky, O.: Fair attribute classification through latent space de-biasing. In: IEEE Conference on Computer Vision and Pattern Recognition (2021)
Ruoss, A., Balunovic, M., Fischer, M., Vechev, M.T.: Learning certified individually fair representations. Adv. Neural Inf. Process. Syst. 33 (2020)
Sarhan, M.H., Navab, N., Eslami, A., Albarqouni, S.: Fairness by learning orthogonal disentangled representations. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12374, pp. 746–761. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58526-6_44
Sattigeri, P., Hoffman, S.C., Chenthamarakshan, V., Varshney, K.R.: Fairness GAN: generating datasets with fairness properties using a generative adversarial network. IBM J. Res. Dev. (2019)
Segal, S., Adi, Y., Pinkas, B., Baum, C., Ganesh, C., Keshet, J.: Fairness in the eyes of the data: certifying machine-learning models. In: AAAI/ACM Conference on AI, Ethics, and Society (2021)
Seonghyeon, K.: Glow pytorch (commit: 97081ff1) (2020). https://github.com/rosinality/glow-pytorch
Song, J., Kalluri, P., Grover, A., Zhao, S., Ermon, S.: Learning controllable fair representations. In: The 22nd International Conference on Artificial Intelligence and Statistics (2019)
Sun, X., Wu, P., Hoi, S.C.H.: Face detection using deep learning: an improved faster RCNN approach. Neurocomputing 299, 42–50 (2018)
Tatman, R.: Gender and dialect bias in youtube’s automatic captions. In: Proceedings of the First ACL Workshop on Ethics in Natural Language Processing (2017)
Tjeng, V., Xiao, K.Y., Tedrake, R.: Evaluating robustness of neural networks with mixed integer programming. In: 7th International Conference on Learning Representations (2019)
UN: The right to privacy in the digital age (2021)
Urban, C., Christakis, M., Wüstholz, V., Zhang, F.: Perfectly parallel fairness certification of neural networks. In: Proceedings of ACM Programming Language (2020)
Wang, H., Grgic-Hlaca, N., Lahoti, P., Gummadi, K.P., Weller, A.: An empirical study on learning fairness metrics for COMPAS data with human supervision. CoRR (2019)
Wang, T., Zhao, J., Yatskar, M., Chang, K., Ordonez, V.: Balanced datasets are not enough: estimating and mitigating gender bias in deep image representations. In: IEEE/CVF International Conference on Computer Vision (2019)
Wang, Z., et al.: Towards fairness in visual recognition: effective strategies for bias mitigation. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (2020)
Wei, S., Niethammer, M.: The fairness-accuracy pareto front. Stat. Anal. Data Min. 15(3), 287–302 (2022). https://doi.org/10.1002/sam.11560
Wilson, B., Hoffman, J., Morgenstern, J.: Predictive inequity in object detection. CoRR (2019)
Wong, E., Kolter, J.Z.: Learning perturbation sets for robust machine learning. In: 9th International Conference on Learning Representations (2021)
Yeom, S., Fredrikson, M.: Individual fairness revisited: transferring techniques from adversarial robustness. In: Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence (2020)
Yurochkin, M., Bower, A., Sun, Y.: Training individually fair ML models with sensitive subspace robustness. In: 8th International Conference on Learning Representations (2020)
Yurochkin, M., Sun, Y.: Sensei: sensitive set invariance for enforcing individual fairness. In: 9th International Conference on Learning Representations (2021)
Zemel, R.S., Wu, Y., Swersky, K., Pitassi, T., Dwork, C.: Learning fair representations. In: Proceedings of the 30th International Conference on Machine Learning (2013)
Zhao, H., Coston, A., Adel, T., Gordon, G.J.: Conditional learning of fair representations. In: 8th International Conference on Learning Representations (2020)
Zhao, J., Wang, T., Yatskar, M., Ordonez, V., Chang, K.: Men also like shopping: reducing gender bias amplification using corpus-level constraints. In: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing (2017)
Acknowledgments
We thank Seyedmorteza Sadat for his help with preliminary investigations and the anonymous reviewers for their insightful feedback.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Peychev, M., Ruoss, A., Balunović, M., Baader, M., Vechev, M. (2022). Latent Space Smoothing for Individually Fair Representations. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds) Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol 13673. Springer, Cham. https://doi.org/10.1007/978-3-031-19778-9_31
Download citation
DOI: https://doi.org/10.1007/978-3-031-19778-9_31
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-19777-2
Online ISBN: 978-3-031-19778-9
eBook Packages: Computer ScienceComputer Science (R0)