Abstract
There have been growing interest in algorithmic fairness for biased data. Although various pre-, in-, and post-processing methods are designed to address this problem, new learning paradigms designed for fair deep models are still necessary. Modern computer vision tasks usually involve large generic models and fine-tuning concerning a specific task. Training modern deep models from scratch is expensive considering the enormous training data and the complicated structures. The recently emerged intra-processing methods are designed to debias pre-trained large models. However, existing techniques stress fine-tuning more, but the deep network structure is less leveraged. This paper proposes a novel intra-processing method to improve model fairness by altering the deep network structure. We find that the unfairness of deep models are usually caused by a small portion of sub-modules, which can be uncovered using the proposed differential framework. We can further employ several strategies to modify the corrupted sub-modules inside the unfair pre-trained structure to build a fair counterpart. We experimentally verify our findings and demonstrate that the reconstructed fair models can make fair classification and achieve superior results to the state-of-the-art baselines. We conduct extensive experiments to evaluate the different strategies. The results also show that our method has good scalability when applied to a variety of fairness measures and different data types.
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
Inherent trade-offs in the fair determination of risk scores. arXiv preprint arXiv:1609.05807 (2016)
Alvi, M., et al.: Turning a blind eye: explicit removal of biases and variation from deep neural network embeddings. In: Proceedings of the European Conference on Computer Vision (ECCV) Workshops (2018)
Arpit, D., et al.: A closer look at memorization in deep networks. In: Proceedings of the 34th International Conference on Machine Learning, vol. 70, pp. 233–242. JMLR. org (2017)
Bellamy, R.K., et al.: Ai fairness 360: an extensible toolkit for detecting, understanding, and mitigating unwanted algorithmic bias. arXiv preprint arXiv:1810.01943 (2018)
Bengio, Y., Léonard, N., Courville, A.: Estimating or propagating gradients through stochastic neurons for conditional computation. arXiv preprint arXiv:1308.3432 (2013)
Bower, A., Niss, L., Sun, Y., Vargo, A.: Debiasing representations by removing unwanted variation due to protected attributes. arXiv preprint arXiv:1807.00461 (2018)
Cai, H., Gan, C., Lin, J., Han, S.: Network augmentation for tiny deep learning. arXiv preprint arXiv:2110.08890 (2021)
Calders, T., Kamiran, F., Pechenizkiy, M.: Building classifiers with independency constraints. In: 2009 IEEE International Conference on Data Mining Workshops, pp. 13–18. IEEE (2009)
Chu, X., Zhang, B., Xu, R.: Fairnas: rethinking evaluation fairness of weight sharing neural architecture search. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 12239–12248 (2021)
Chu, X., Zhou, T., Zhang, B., Li, J.: Fair DARTS: eliminating unfair advantages in differentiable architecture search. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12360, pp. 465–480. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58555-6_28
Dastin, J.: Amazon scraps secret ai recruiting tool that showed bias against women. Reuters (2018)
Denton, E., Hutchinson, B., Mitchell, M., Gebru, T.: Detecting bias with generative counterfactual face attribute augmentation (2019)
Dwork, C., et al.: Fairness through awareness. In: Proceedings of the 3rd Innovations in Theoretical Computer Science Conference, pp. 214–226 (2012)
Fitzpatrick, T.B.: The validity and practicality of sun-reactive skin types i through vi. Arch. Dermatol. 124(6), 869–871 (1988)
Frankle, J., Carbin, M.: The lottery ticket hypothesis: finding sparse, trainable neural networks. In: International Conference on Learning Representations (2019). https://openreview.net/forum?id=rJl-b3RcF7
Ganjdanesh, A., Gao, S., Huang, H.: Interpretations steered network pruning via amortized inferred saliency maps. In: Proceedings of the European Conference on Computer Vision (ECCV) (2022)
Gwilliam, M., et al.: Rethinking common assumptions to mitigate racial bias in face recognition datasets. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 4123–4132 (2021)
Han, S., Mao, H., Dally, W.J.: Deep compression: compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv preprint arXiv:1510.00149 (2015)
Han, S., et al.: Dsd: regularizing deep neural networks with dense-sparse-dense training flow (2016)
Han, S., Pool, J., Tran, J., Dally, W.: Learning both weights and connections for efficient neural network. Adv. Neural Inf. Process. Syst. 28 (2015)
Hardt, M., Others: equality of opportunity in supervised learning. Adv. Neural Inf. Process. Syst. (2016)
He, K., Zheng, X.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)
Huang, G., et al.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700–4708 (2017)
Huang, G., et al.: Condensenet: an efficient densenet using learned group convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2752–2761 (2018)
Kamiran, F., Karim, A., Zhang, X.: Decision theory for discrimination-aware classification. In: 2012 IEEE 12th International Conference on Data Mining, pp. 924–929. IEEE (2012)
Kärkkäinen, K., Joo, J.: Fairface: face attribute dataset for balanced race, gender, and age. arXiv preprint arXiv:1908.04913 (2019)
Kim, M., et al.: Fairness through computationally-bounded awareness. Adv. Neural Inf. Process. Syst., 4842–4852 (2018)
Kohavi, R.: Scaling up the accuracy of naive-bayes classifiers: A decision-tree hybrid. In: Kdd, vol. 96, pp. 202–207 (1996)
Krizhevsky, A., Hinton, G., et al.: Learning multiple layers of features from tiny images (2009)
Li, H., Kadav, A., Durdanovic, I., Samet, H., Graf, H.P.: Pruning filters for efficient convnets. In: International Conference on Learning Representations (ICLR) (2017)
Liu, Z., et al.: Deep learning face attributes in the wild. In: Proceedings of International Conference on Computer Vision (ICCV) (2015)
Meng, F., et al.: Filter grafting for deep neural networks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6599–6607 (2020)
Mukherjee, D., et al.: Two simple ways to learn individual fairness metrics from data. arXiv preprint arXiv:2006.11439 (2020)
Paszke, A., et al.: Automatic differentiation in pytorch (2017)
Pleiss, G., et al.: On fairness and calibration. Adv. Neural Inf. Process. Syst. 30 (2017)
Savani, Y., White, C., Govindarajulu, N.S.: Intra-processing methods for debiasing neural networks. Adv. Neural Inf. Process. Syst. 33, 2798–2810 (2020)
Shen, C., Wang, X., Yin, Y., Song, J., Luo, S., Song, M.: Progressive network grafting for few-shot knowledge distillation. arXiv preprint arXiv:2012.04915 (2020)
Vigdor, N.: Apple card investigated after gender discrimination complaints. The New York Times (2019)
Wang, M., et al.: Racial faces in the wild: reducing racial bias by information maximization adaptation network. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 692–702 (2019)
Wang, Z., et al.: Towards fairness in visual recognition: Effective strategies for bias mitigation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8919–8928 (2020)
Warde-Farley, D., Goodfellow, I.J., Courville, A., Bengio, Y.: An empirical analysis of dropout in piecewise linear networks. arXiv preprint arXiv:1312.6197 (2013)
Wilson, B., Hoffman, J., Morgenstern, J.: Predictive inequity in object detection. arXiv preprint arXiv:1902.11097 (2019)
Yang, F., Cisse, M., Koyejo, O.O.: Fairness with overlapping groups; a probabilistic perspective. Adv. Neural Inf. Process. Syst. 33 (2020)
Yang, L., et al.: Condensenet v2: sparse feature reactivation for deep networks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 3569–3578 (2021)
Yu, J., Huang, T.S.: Universally slimmable networks and improved training techniques. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 1803–1811 (2019)
Yu, J., Yang, L., Xu, N., Yang, J., Huang, T.: Slimmable neural networks. In: International Conference on Learning Representations (2019). https://openreview.net/forum?id=H1gMCsAqY7
Yurochkin, M., et al.: Training individually fair ml models with sensitive subspace robustness. In: International Conference on Learning Representations (2019)
Zafar, M.B., et al.: Fairness beyond disparate treatment & disparate impact: learning classification without disparate mistreatment. In: Proceedings of the 26th International Conference on World Wide Web, pp. 1171–1180 (2017)
Zhang, B.H., Lemoine, B., Mitchell, M.: Mitigating unwanted biases with adversarial learning. In: Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society, pp. 335–340 (2018)
Zhang, X.: Shufflenet: an extremely efficient convolutional neural network for mobile devices. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6848–6856 (2018)
Zhang, Y., Gao, S., Huang, H.: Exploration and estimation for model compression. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 487–496 (2021)
Zhang, Y., Luo, L., Huang, H.: Unified fairness from data to learning algorithm. In: 2021 IEEE International Conference on Data Mining (ICDM), pp. 1499–1504. IEEE (2021)
Zhao, J., et al.: Men also like shopping: reducing gender bias amplification using corpus-level constraints. arXiv preprint arXiv:1707.09457 (2017)
Acknowledgement
This work was partially supported by NSF IIS 1845666, 1852606, 1838627, 1837956, 1956002, 2217003.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Zhang, Y., Gao, S., Huang, H. (2022). Recover Fair Deep Classification Models via Altering Pre-trained Structure. 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_28
Download citation
DOI: https://doi.org/10.1007/978-3-031-19778-9_28
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)