Abstract
With the advancement of Artificial Intelligence (AI), algorithms brings more fairness challenges in ethical, legal, psychological and social levels. People should start to face these challenges seriously in dealing with AI products and AI solutions. More and more companies start to recognize the importance of Diversity and Inclusion (D&I) due to AI algorithms and take corresponding actions. This paper introduces Lenovo AI’s Vision on D&I, specially, the efforts of mitigating algorithm bias in human face processing technology. Latest evaluation shows that Lenovo face recognition engine achieves better performance of racial fairness over competitors in terms of multiple metrics. In addition, it also presents post-processing strategy of improving fairness according to different considerations and criteria.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press (2016). http://www.deeplearningbook.org
Hastie, T., Tibshirani, R., Friedman, J.: The Elements of Statistical Learning. SSS. Springer, New York (2009). https://doi.org/10.1007/978-0-387-84858-7_910.1007/978-0-387-84858-7_9
Muheidat, F., Tawalbeh, L.: Team based learning: the role of equity, diversity, and inclusion in team formation. In: 2018 Research on Equity and Sustained Participation in Engineering, Computing, and Technology (RESPECT), pp. 1–2 (2018)
Hespanhol, L., Davis, H., Fredericks, J., Caldwell, G.A., Hoggenmueller, M.: Digital outreach: designing technologies for diversity, participation and social inclusion, pp. 648–650, November 2017
Siau, K.: How can AI help to enhance diversity and inclusion? In: 25th Americas Conference on Information Systems, AMCIS, August 2019
Narayanan, A.: Translation tutorial: 21 fairness definitions and their politics. In: Conference on Fairness, Accountability, and Transparency (2018)
Kleinberg, J.M., Mullainathan, S., Raghavan, M.: Inherent trade-offs in the fair determination of risk scores. CoRR, abs/1609.05807 (2016)
Friedler, S.A., Scheidegger, C., Venkatasubramanian, S., Choudhary, S., Hamilton, E.P., Roth, D.: A comparative study of fairness-enhancing interventions in machine learning. In: Proceedings of the Conference on Fairness, Accountability, and Transparency (2019)
Browne, K., Draper, J.: https://www.slideshare.net/KrishnaramKenthapadi/fairness-and-privacy-in-aiml-systems-187923831/
Adebayo, J.A.: FairML: toolbox for diagnosing bias in predictive modeling. Master thesis, Massachusetts Institute of Technology (2016). https://github.com/adebayoj/fairml
Bantilan, N.: Themis-ml: a fairness-aware machine learning interface for end-to-end discrimination discovery and mitigation. CoRR, abs/1710.06921 (2017)
Zehlike, M., Castillo, C., Bonchi, F., Hajian, S., Megahed, M.: Fairness measures: datasets and software for detecting algorithmic discrimination. http://fairness-measures.org/
Zehlike, M., Castillo, C., Bonchi, F., Hajian, S., Megahed, M.: Fairness measures: datasets and software for detecting algorithmic discrimination. http://fairness-measures.org/
Speicher, T., et al.: A unified approach to quantifying algorithmic unfairness: measuring individual & group unfairness via inequality indices. CoRR, abs/1807.00787 (2018)
Alessandro, B., ONeil, C., Laatta, T.: Conscientious classification: a data scientists guide to discrimination-aware classification. Big Data 5, 120–134 (2017)
Kamiran, F., Calders, T.: Data preprocessing techniques for classification without discrimination. Knowl. Inf. Syst. 33(1), 1–33 (2011)
Calmon, F., Wei, D., Vinzamuri, B., Ramamurthy, K.N., Varshney, K.R.: Optimized pre-processing for discrimination prevention. In: Guyon, I., et al. (eds.) Advances in Neural Information Processing Systems, vol. 30, pp. 3992–4001. Curran Associates Inc. (2017)
Feldman, M., Friedler, S.A., Moeller, J., Scheidegger, C., Venkatasubramanian, S.: Certifying and removing disparate impact. In: Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Association for Computing Machinery, New York (2015)
Zhang, B.H., Lemoine, B., Mitchell, M.: Mitigating unwanted biases with adversarial learning. CoRR, abs/1801.07593 (2018)
Kamishima, T., Akaho, S., Asoh, H., Sakuma, J.: Fairness-aware classifier with prejudice remover regularizer. In: Flach, P.A., De Bie, T., Cristianini, N. (eds.) ECML PKDD 2012. LNCS (LNAI), vol. 7524, pp. 35–50. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-33486-3_3
Hardt, M., Price, E., Srebro, N.: Equality of opportunity in supervised learning. CoRR, abs/1610.02413 (2016)
Pleiss, G., Raghavan, M., Wu, F., Kleinberg, J., Weinberger, K.Q.: On fairness and calibration. In: Guyon, I., et al. (eds.) Advances in Neural Information Processing Systems, vol. 30, pp. 5680–5689. Curran Associates Inc. (2017)
Kamiran, F., Karim, A., Zhang, X.: Decision theory for discrimination-aware classification. In: 2012 IEEE 12th International Conference on Data Mining, pp. 924–929 (2012)
Wang, M., Deng, W., Hu, J., Tao, X., Huang, Y.: Racial faces in the wild: Reducing racial bias by information maximization adaptation network. In: 2019 IEEE/CVF International Conference on Computer Vision (ICCV), pp. 692–702 (2019)
Face++ research toolkit. www.faceplusplus.com
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Shi, S. et al. (2020). Algorithm Bias Detection and Mitigation in Lenovo Face Recognition Engine. In: Zhu, X., Zhang, M., Hong, Y., He, R. (eds) Natural Language Processing and Chinese Computing. NLPCC 2020. Lecture Notes in Computer Science(), vol 12431. Springer, Cham. https://doi.org/10.1007/978-3-030-60457-8_36
Download citation
DOI: https://doi.org/10.1007/978-3-030-60457-8_36
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-60456-1
Online ISBN: 978-3-030-60457-8
eBook Packages: Computer ScienceComputer Science (R0)