Skip to main content
SpringerLink
Log in

Recover Fair Deep Classification Models via Altering Pre-trained Structure

  • Conference paper
  • First Online:
Computer Vision – ECCV 2022 (ECCV 2022)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13673))

Included in the following conference series:

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

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 89.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 119.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Inherent trade-offs in the fair determination of risk scores. arXiv preprint arXiv:1609.05807 (2016)

  2. 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)

    Google Scholar 

  3. 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)

    Google Scholar 

  4. 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)

  5. Bengio, Y., Léonard, N., Courville, A.: Estimating or propagating gradients through stochastic neurons for conditional computation. arXiv preprint arXiv:1308.3432 (2013)

  6. Bower, A., Niss, L., Sun, Y., Vargo, A.: Debiasing representations by removing unwanted variation due to protected attributes. arXiv preprint arXiv:1807.00461 (2018)

  7. Cai, H., Gan, C., Lin, J., Han, S.: Network augmentation for tiny deep learning. arXiv preprint arXiv:2110.08890 (2021)

  8. 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)

    Google Scholar 

  9. 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)

    Google Scholar 

  10. 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

    Chapter  Google Scholar 

  11. Dastin, J.: Amazon scraps secret ai recruiting tool that showed bias against women. Reuters (2018)

    Google Scholar 

  12. Denton, E., Hutchinson, B., Mitchell, M., Gebru, T.: Detecting bias with generative counterfactual face attribute augmentation (2019)

    Google Scholar 

  13. Dwork, C., et al.: Fairness through awareness. In: Proceedings of the 3rd Innovations in Theoretical Computer Science Conference, pp. 214–226 (2012)

    Google Scholar 

  14. Fitzpatrick, T.B.: The validity and practicality of sun-reactive skin types i through vi. Arch. Dermatol. 124(6), 869–871 (1988)

    Article  Google Scholar 

  15. 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

  16. 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)

    Google Scholar 

  17. 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)

    Google Scholar 

  18. 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)

  19. Han, S., et al.: Dsd: regularizing deep neural networks with dense-sparse-dense training flow (2016)

    Google Scholar 

  20. Han, S., Pool, J., Tran, J., Dally, W.: Learning both weights and connections for efficient neural network. Adv. Neural Inf. Process. Syst. 28 (2015)

    Google Scholar 

  21. Hardt, M., Others: equality of opportunity in supervised learning. Adv. Neural Inf. Process. Syst. (2016)

    Google Scholar 

  22. 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)

    Google Scholar 

  23. Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)

  24. Huang, G., et al.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700–4708 (2017)

    Google Scholar 

  25. 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)

    Google Scholar 

  26. 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)

    Google Scholar 

  27. Kärkkäinen, K., Joo, J.: Fairface: face attribute dataset for balanced race, gender, and age. arXiv preprint arXiv:1908.04913 (2019)

  28. Kim, M., et al.: Fairness through computationally-bounded awareness. Adv. Neural Inf. Process. Syst., 4842–4852 (2018)

    Google Scholar 

  29. Kohavi, R.: Scaling up the accuracy of naive-bayes classifiers: A decision-tree hybrid. In: Kdd, vol. 96, pp. 202–207 (1996)

    Google Scholar 

  30. Krizhevsky, A., Hinton, G., et al.: Learning multiple layers of features from tiny images (2009)

    Google Scholar 

  31. Li, H., Kadav, A., Durdanovic, I., Samet, H., Graf, H.P.: Pruning filters for efficient convnets. In: International Conference on Learning Representations (ICLR) (2017)

    Google Scholar 

  32. Liu, Z., et al.: Deep learning face attributes in the wild. In: Proceedings of International Conference on Computer Vision (ICCV) (2015)

    Google Scholar 

  33. 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)

    Google Scholar 

  34. Mukherjee, D., et al.: Two simple ways to learn individual fairness metrics from data. arXiv preprint arXiv:2006.11439 (2020)

  35. Paszke, A., et al.: Automatic differentiation in pytorch (2017)

    Google Scholar 

  36. Pleiss, G., et al.: On fairness and calibration. Adv. Neural Inf. Process. Syst. 30 (2017)

    Google Scholar 

  37. Savani, Y., White, C., Govindarajulu, N.S.: Intra-processing methods for debiasing neural networks. Adv. Neural Inf. Process. Syst. 33, 2798–2810 (2020)

    Google Scholar 

  38. 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)

  39. Vigdor, N.: Apple card investigated after gender discrimination complaints. The New York Times (2019)

    Google Scholar 

  40. 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)

    Google Scholar 

  41. 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)

    Google Scholar 

  42. 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)

  43. Wilson, B., Hoffman, J., Morgenstern, J.: Predictive inequity in object detection. arXiv preprint arXiv:1902.11097 (2019)

  44. Yang, F., Cisse, M., Koyejo, O.O.: Fairness with overlapping groups; a probabilistic perspective. Adv. Neural Inf. Process. Syst. 33 (2020)

    Google Scholar 

  45. 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)

    Google Scholar 

  46. 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)

    Google Scholar 

  47. 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

  48. Yurochkin, M., et al.: Training individually fair ml models with sensitive subspace robustness. In: International Conference on Learning Representations (2019)

    Google Scholar 

  49. 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)

    Google Scholar 

  50. 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)

    Google Scholar 

  51. 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)

    Google Scholar 

  52. 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)

    Google Scholar 

  53. 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)

    Google Scholar 

  54. Zhao, J., et al.: Men also like shopping: reducing gender bias amplification using corpus-level constraints. arXiv preprint arXiv:1707.09457 (2017)

Download references

Acknowledgement

This work was partially supported by NSF IIS 1845666, 1852606, 1838627, 1837956, 1956002, 2217003.

Author information

Authors and Affiliations

  1. Department of Electrical and Computer Engineering, University of Pittsburgh, Pittsburgh, USA

    Yanfu Zhang, Shangqian Gao & Heng Huang

Authors
  1. Yanfu Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Shangqian Gao
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Heng Huang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Heng Huang .

Editor information

Editors and Affiliations

  1. Tel Aviv University, Tel Aviv, Israel

    Shai Avidan

  2. University College London, London, UK

    Gabriel Brostow

  3. Google AI, Accra, Ghana

    Moustapha Cissé

  4. University of Catania, Catania, Italy

    Giovanni Maria Farinella

  5. Facebook (United States), Menlo Park, CA, USA

    Tal Hassner

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

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)

Publish with us

Policies and ethics

Search

Navigation