Research on Fairness in Deep Learning Models
Author:
Affiliation:

  • Article
  • | |
  • Metrics
  • |
  • Reference [38]
  • |
  • Related [20]
  • |
  • Cited by
  • | |
  • Comments
    Abstract:

    In recent years, deep neural networks have been widely employed in real decision-making systems. Unfairness in decision-making systems will exacerbate social inequality and harm society. Therefore, researchers begin to carry out a lot of studies on the fairness of deep learning systems, where as most studies focus on group fairness and cannot guarantee fairness within the group. To this end, this study defines two individual fairness calculation methods. The first one is individual fairness rate IFRb based on labels of output, which is the probability of having the same predicted label for two similar samples. The second is individual fairness rate IFRp based on distributions of output, which is the probability of having similar predicted output distribution for two similar samples respectively, and the latter has stricter individual fairness. In addition, this study proposes an algorithm IIFR to improve the individual fairness of these models. The algorithm employs cosine similarity to measure the similarity between samples and then selects similar sample pairs via the similarity threshold decided by different applications. Finally, the output difference of the similar sample pairs is added to the objective function as an individual fairness loss item during the training, which penalizes the similar training samples with large differences in model output to improve the individual fairness of the model. The experimental results show that the proposed IIFR algorithm outperforms the state-of-the-art methods on individual fairness improvement, and can maintain group fairness of models while improving individual fairness.

    Reference
    [1] Bojarski M, Del Testa D, Dworakowski D, Firner B, Flepp B, Goyal P, Jackel LD, Monfort M, Muller U, Zhang JK, Zhang X, Zhao J, Zieba K. End to end learning for self-driving cars. arXiv:1604.07316, 2016.
    [2] Goodall NJ. Can you program ethics into a self-driving car?. IEEE Spectrum, 2016, 53(6): 28-58. [doi: 10.1109/MSPEC.2016.7473149]
    [3] Litjens G, Kooi T, Bejnordi BE, Setio AAA, Ciompi F, Ghafoorian M, Van Der Laak JAWM, Van Ginneken B, Sánchez CI. A survey on deep learning in medical image analysis. Medical Image Analysis, 2017, 42: 60-88. [doi: 10.1016/j.media.2017.07.005]
    [4] Fu K, Cheng DW, Tu Y, Zhang LQ. Credit card fraud detection using convolutional neural networks. In: Proc. of the 23rd Int’l Conf. on Neural Information Processing. Kyoto: Springer, 2016. 483-490.
    [5] Saxena NA, Huang KR, DeFilippis E, Radanovic G, Parkes DC, Liu Y. How do fairness definitions fare? Examining public attitudes towards algorithmic definitions of fairness. In: Proc. of the 2019 AAAI/ACM Conf. on AI, Ethics, and Society. Honolulu: ACM, 2019. 99-106.
    [6] Dastin J. Amazon scraps secret AI recruiting tool that showed bias against women. Ethics of Data and Analytics. New York: Auerbach Publications, 2022. 296-299.
    [7] Angwin J, Larson J, Mattu S, Kirchner L. Machine bias. Ethics of Data and Analytics. New York: Auerbach Publications. 2016. 254-264.
    [8] 刘文炎, 沈楚云, 王祥丰, 金博, 卢兴见, 王晓玲, 查宏远, 何积丰. 可信机器学习的公平性综述. 软件学报, 2021, 32(5): 1404-1426. http://www.jos.org.cn/1000-9825/6214.htm
    Liu WY, Shen CY, Wang XF, Jin B, Lu XJ, Wang XL, Zha HY, He JF. Survey on fairness in trustworthy machine learning. Ruan Jian Xue Bao/Journal of Software, 2021, 32(5): 1404-1426 (in Chinese with English abstract). http://www.jos.org.cn/1000-9825/6214.htm
    [9] Grgić-Hlača N, Zafar MB, Gummadi KP, Weller A. The case for process fairness in learning: Feature selection for fair decision making. In: Proc. of the 2016 Symp. on Machine Learning and the Law at the 29th Conf. on Neural Information Processing Systems. Barcelona, 2016. 1-11.
    [10] Dwork C, Hardt M, Pitassi T, Reingold O, Zemel R. Fairness through awareness. In: Proc. of the 3rd Innovations in Theoretical Computer Science Conf. Cambridge: ACM, 2012. 214-226.
    [11] Zemel R, Wu Y, Swersky K, Pitassi T, Dwork C. Learning fair representations. In: Proc. of the 30th Int’l Conf. on Machine Learning. Atlanta: JMLR.org, 2013. III-325-III-333.
    [12] Lahoti P, Gummadi KP, Weikum G. iFair: Learning individually fair data representations for algorithmic decision making. In: Proc. of the 35th IEEE Int’l Conf. on Data Engineering. Macao: IEEE, 2019. 1334-1345.
    [13] Zhang LF, Zhang YL, Zhang M. Efficient white-box fairness testing through gradient search. In: Proc. of the 30th ACM SIGSOFT Int’l Symp. on Software Testing and Analysis. Denmark: ACM, 2021. 103-114.
    [14] Edwards H, Storkey A. Censoring representations with an adversary. arXiv:1511.05897, 2016.
    [15] Zafar MB, Valera I, Rogriguez MG, Gummadi KP. Fairness constraints: Mechanisms for fair classification. In: Proc. of the 20th Int’l Conf. on Artificial Intelligence and Statistics. Florida: JMLR, 2017. 962-970.
    [16] Hardt M, Price E, Srebro N. Equality of opportunity in supervised learning. In: Proc. of the 30th Int’l Conf. on Neural Information Processing Systems. Barcelona: Curran Associates Inc., 2016. 3323-3331.
    [17] Berk R, Heidari H, Jabbari S, Kearns M, Roth A. Fairness in criminal justice risk assessments: The state of the art. Sociological Methods & Research, 2021, 50(1): 3-44. [doi: 10.1177/0049124118782533]
    [18] Galhotra S, Brun Y, Meliou A. Fairness testing: Testing software for discrimination. In: Proc. of the 11th Joint Meeting on Foundations of Software Engineering. Paderborn: ACM, 2017. 498-510.
    [19] Kilbertus N, Rodriguez MG, Schölkopf B, Muandet K, Valera I. Fair decisions despite imperfect predictions. In: Proc. of the 23rd Int’l Conf. on Artificial Intelligence and Statistics. Palermo: PMLR, 2020. 277-287.
    [20] Kusner MJ, Loftus J, Russell C, Silva R. Counterfactual fairness. In: Proc. of the 31st Int’l Conf. on Neural Information Processing Systems, Long Beach: Curran Associates Inc., 2017. 4069-4079.
    [21] Beutel A, Chen JL, Zhao Z, Chi EH. Data decisions and theoretical implications when adversarially learning fair representations. arXiv:1707.00075, 2017.
    [22] Madras D, Creager E, Pitassi T, Zemel R. Learning adversarially fair and transferable representations. In: Proc. of the 35th Int’l Conf. on Machine Learning. Stockholm: PMLR, 2018. 3384-3393.
    [23] Feng R, Yang Y, Lyu Y, Tan CH, Sun YZ, Wang CP. Learning fair representations via an adversarial framework. arXiv:1904.13341, 2019.
    [24] Menon AK, Williamson RC. The cost of fairness in classification. arXiv:1705.09055, 2017.
    [25] Speicher T, Heidari H, Grgic-Hlaca N, Gummadi KP, Singla A, Weller A, Zafar MB. A unified approach to quantifying algorithmic unfairness: Measuring individual & group unfairness via inequality indices. In: Proc. of the 24th ACM SIGKDD Int’l Conf. on Knowledge Discovery & Data Mining. London: ACM, 2018. 2239-2248.
    [26] Joseph M, Kearns M, Morgenstern J, Roth A. Fairness in learning: Classic and contextual bandits. In: Proc. of the 30th Int’l Conf. on neural Information Processing Systems. Barcelona: Curran Associates Inc., 2016. 325-333.
    [27] Kearns M, Neel S, Roth A, Wu ZS. Preventing fairness gerrymandering: Auditing and learning for subgroup fairness. In: Proc. of the 35th Int’l Conf. on Machine Learning. Stockholm: PMLR, 2018. 2564-2572.
    [28] Goodfellow IJ, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A, Bengio Y. Generative adversarial nets. In: Proc. of the 27th Int’l Conf. on Neural Information Processing Systems. Montreal: MIT Press, 2014. 2672-2680.
    [29] Zhao H, Coston A, Adel T, Gordon GJ. Conditional learning of fair representations. arXiv:1910.07162, 2020.
    [30] Blei DM, Kucukelbir A, McAuliffe JD. Variational inference: A review for statisticians. Journal of the American statistical Association, 2017, 112(518): 859-877. [doi: 10.1080/01621459.2017.1285773]
    [31] Gabrilovich E, Markovitch S. Computing semantic relatedness using Wikipedia-based explicit semantic analysis. In: Proc. of the 20th Int’l Joint Conf. on Artifical Intelligence. Hyderabad: Morgan Kaufmann Publishers Inc., 2007. 1606-1611.
    [32] Potthast M, Stein B, Anderka M. A Wikipedia-based multilingual retrieval model. In: Proc. of the 30th European Conf. on IR Research. Glasgow: Springer, 2008. 522-530.
    [33] De Boer PT, Kroese DP, Mannor S, Rubinstein RY. A tutorial on the cross-entropy method. Annals of Operations Research, 2005, 134(1): 19-67. [doi: 10.1007/s10479-005-5724-z]
    [34] Zeiler MD. ADADELTA: An adaptive learning rate method. arXiv:1212.5701, 2012.
    [35] Burnaev E, Erofeev P, Papanov A. Influence of resampling on accuracy of imbalanced classification. In: Proc. of the 8th Int’l Conf. on Machine Vision. Barcelona: SPIE, 2015. 423-427.
    [36] Cui Y, Jia ML, Lin TY, Song Y, Belongie S. Class-balanced loss based on effective number of samples. In: Proc. of the 2019 IEEE/CVF Conf. on Computer Vision and Pattern Recognition. Long Beach: IEEE, 2019. 9260-9269.
    [37] Chouldechova A. Fair prediction with disparate impact: A study of bias in recidivism prediction instruments. Big Data, 2017, 5(2): 153-163. [doi: 10.1089/big.2016.0047]
    Cited by
    Comments
    Comments
    分享到微博
    Submit
Get Citation

王昱颖,张敏,杨晶然,徐晟恺,陈仪香.深度学习模型中的公平性研究.软件学报,2023,34(9):4037-4055

Copy
Share
Article Metrics
  • Abstract:2116
  • PDF: 4978
  • HTML: 2620
  • Cited by: 0
History
  • Received:August 23,2022
  • Revised:October 13,2022
  • Online: January 13,2023
  • Published: September 06,2023
You are the first2044671Visitors
Copyright: Institute of Software, Chinese Academy of Sciences Beijing ICP No. 05046678-4
Address:4# South Fourth Street, Zhong Guan Cun, Beijing 100190,Postal Code:100190
Phone:010-62562563 Fax:010-62562533 Email:jos@iscas.ac.cn
Technical Support:Beijing Qinyun Technology Development Co., Ltd.

Beijing Public Network Security No. 11040202500063