Fairness Warnings and Fair-MAML: Learning Fairly with Minimal Data

被引:23
作者
Slack, Dylan [1 ]
Friedler, Sorelle A. [2 ]
Givental, Emile [2 ]
机构
[1] Univ Calif Irvine, Irvine, CA 92717 USA
[2] Haverford Coll, Haverford, PA 19041 USA
来源
FAT* '20: PROCEEDINGS OF THE 2020 CONFERENCE ON FAIRNESS, ACCOUNTABILITY, AND TRANSPARENCY | 2020年
关键词
machine learning; fairness; meta-learning; covariate shift;
D O I
10.1145/3351095.3372839
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Motivated by concerns surrounding the fairness effects of sharing and transferring fair machine learning tools, we propose two algorithms: Fairness Warnings and Fair-MAML. The first is a model-agnostic algorithm that provides interpretable boundary conditions for when a fairly trained model may not behave fairly on similar but slightly different tasks within a given domain. The second is a fair meta-learning approach to train models that can be quickly fine-tuned to specific tasks from only a few number of sample instances while balancing fairness and accuracy. We demonstrate experimentally the individual utility of each model using relevant baselines and provide the first experiment to our knowledge of K-shot fairness, i.e. training a fair model on a new task with only K data points. Then, we illustrate the usefulness of both algorithms as a combined method for training models from a few data points on new tasks while using Fairness Warnings as interpretable boundary conditions under which the newly trained model may not be fair.
引用
收藏
页码:200 / 209
页数:10
相关论文
共 38 条
  • [11] Coston Amanda, 2019, P AAAI ACM C ART INT
  • [12] Dwork C., 2018, C FAIRN ACC TRANSP, P119
  • [13] Dwork C., 2012, P 3 INN THEOR COMP S, P214, DOI [DOI 10.1145/2090236.2090255, 10.1145/2090236.2090255]
  • [14] Certifying and Removing Disparate Impact
    Feldman, Michael
    Friedler, Sorelle A.
    Moeller, John
    Scheidegger, Carlos
    Venkatasubramanian, Suresh
    [J]. KDD'15: PROCEEDINGS OF THE 21ST ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING, 2015, : 259 - 268
  • [15] Finn C, 2017, PR MACH LEARN RES, V70
  • [16] A comparative study of fairness-enhancing interventions in machine learning
    Friedler, Sorelle A.
    Scheidegger, Carlos
    Venkatasubramanian, Suresh
    Choudhary, Sonam
    Hamilton, Evan P.
    Roth, Derek
    [J]. FAT*'19: PROCEEDINGS OF THE 2019 CONFERENCE ON FAIRNESS, ACCOUNTABILITY, AND TRANSPARENCY, 2019, : 329 - 338
  • [17] Hardt M., 2016, P 30 INT C NEUR INF, P3323
  • [18] Huang L., 2019, INT C MACHINE LEARNI, P2879
  • [19] Kallus N, 2018, PR MACH LEARN RES, V80
  • [20] Kamishima Toshihiro, 2012, Machine Learning and Knowledge Discovery in Databases. Proceedings of the European Conference (ECML PKDD 2012), P35, DOI 10.1007/978-3-642-33486-3_3