Abstract
Fairness across different demographic groups is an essential criterion for face-related tasks, Face Attribute Classification (FAC) being a prominent example. Simultaneously, federated Learning (FL) is gaining traction as a scalable paradigm for distributed training. In FL, client models trained on private datasets get aggregated by a central aggregator. Existing FL approaches require data homogeneity to ensure fairness. However, this assumption is restrictive in real-world settings. E.g., geographically distant or closely associated clients may have heterogeneous data. In this paper, we observe that existing techniques for ensuring fairness are not viable for FL with data heterogeneity. We introduce F3, an FL framework for fair FAC under data heterogeneity. We propose two methodologies in F3, (i) Heuristic-based and (ii) Gradient-based, to improve fairness across demographic groups without requiring data homogeneity assumption. We demonstrate the efficacy of our approaches through empirically observed fairness measures and accuracy guarantees on popular face datasets. Using Mahalanobis distance, we show that F3 obtains a practical balance between accuracy and fairness for FAC. The code is available at: github.com/magnetar-iiith/F3.
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
Agarwal, A., Beygelzimer, A., Dudik, M., Langford, J., Wallach, H.: A reductions approach to fair classification. In: ICML, pp. 60–69 (2018)
Augenstein, S., Hard, A., Partridge, K., Mathews, R.: Jointly learning from decentralized (federated) and centralized data to mitigate distribution shift. In: NeurIPS 2021 Workshop on Distribution Shifts: Connecting Methods and Applications (2021)
Chouldechova, A.: Fair prediction with disparate impact: a study of bias in recidivism prediction instruments. Big Data 5(2), 153–163 (2017)
Ezzeldin, Y.H., Yan, S., He, C., Ferrara, E., Avestimehr, S.: FairFed: enabling group fairness in federated learning. In: NeurIPS Workshop on New Frontiers in Federated Learning (NFFL) (2021)
Hardt, M., Price, E., Srebro, N.: Equality of opportunity in supervised learning. In: NeurIPS, vol. 29, pp. 3315–3323 (2016)
Hu, S., Wu, Z.S., Smith, V.: Provably fair federated learning via bounded group loss. In: ICLR Workshop on Socially Responsible Machine Learning (2022)
Jung, S., Chun, S., Moon, T.: Learning fair classifiers with partially annotated group labels. In: CVPR, pp. 10348–10357 (2022)
Kanaparthy, S., Padala, M., Damle, S., Sarvadevabhatla, R.K., Gujar, S.: F3: fair and federated face attribute classification with heterogeneous data. arXiv preprint arXiv:2109.02351 (2021)
Karkkainen, K., Joo, J.: Fairface: face attribute dataset for balanced race, gender, and age for bias measurement and mitigation. In: WACV, pp. 1548–1558 (2021)
Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: CVPR, pp. 4401–4410 (2019)
Konečnỳ, J., McMahan, H.B., Ramage, D., Richtárik, P.: Federated optimization: distributed machine learning for on-device intelligence. arXiv preprint arXiv:1610.02527 (2016)
Lokhande, V.S., Akash, A.K., Ravi, S.N., Singh, V.: FairALM: augmented Lagrangian method for training fair models with little regret. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12357, pp. 365–381. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58610-2_22
McMahan, B., Moore, E., Ramage, D., Hampson, S., Arcas, B.A.: Communication-efficient learning of deep networks from decentralized data. In: AISTATS (2017)
Padala, M., Damle, S., Gujar, S.: Federated learning meets fairness and differential privacy. In: ICONIP, pp. 692–699 (2021)
Padala, M., Gujar, S.: FNNC: achieving fairness through neural networks. In: IJCAI, pp. 2277–2283 (2020)
Ruan, Y., Joe-Wong, C.: Fedsoft: soft clustered federated learning with proximal local updating. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, pp. 8124–8131 (2022)
Terhörst, P., et al.: A comprehensive study on face recognition biases beyond demographics. IEEE Trans. Technol. Soc. 3(1), 16–30 (2021)
Torralba, A., Efros, A.A.: Unbiased look at dataset bias. In: CVPR, pp. 1521–1528 (2011)
Zafar, M.B., Valera, I., Rogriguez, M.G., Gummadi, K.P.: Fairness constraints: mechanisms for fair classification. In: AISTATS, pp. 962–970 (2017)
Zhang, B.H., Lemoine, B., Mitchell, M.: Mitigating unwanted biases with adversarial learning. In: AIES, pp. 335–340 (2018)
Zhang, D.Y., Kou, Z., Wang, D.: FairFL: a fair federated learning approach to reducing demographic bias in privacy-sensitive classification models. In: IEEE Big Data, pp. 1051–1060 (2020)
Zhang, J., Wu, Y., Pan, R.: Incentive mechanism for horizontal federated learning based on reputation and reverse auction. In: WWW, pp. 947–956 (2021)
Zhang, Z., Song, Y., Qi, H.: Age progression/regression by conditional adversarial autoencoder. In: CVPR, pp. 5810–5818 (2017)
Zhao, H., Gordon, G.: Inherent tradeoffs in learning fair representations. In: NeurIPS, vol. 32, pp. 15675–15685 (2019)
Zheng, X., Guo, Y., Huang, H., Li, Y., He, R.: A survey of deep facial attribute analysis. Int. J. Comput. Vision 128(8), 2002–2034 (2020)
Author information
Authors and Affiliations
Corresponding author
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
Kanaparthy, S., Padala, M., Damle, S., Sarvadevabhatla, R.K., Gujar, S. (2023). F3: Fair and Federated Face Attribute Classification with Heterogeneous Data. 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_38
Download citation
DOI: https://doi.org/10.1007/978-3-031-33374-3_38
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)