This method uses a dual strategy performing training and representation alteration (TARA) for the mitigation of prominent causes of AI bias by including: a) the use of representation learning alteration via adversarial independence to suppress the bias-inducing dependence of the data representation from protected factors; and b) training set alteration via intelligent augmentation to address bias-causing data imbalance, by using generative models that allow the fine control of sensitive factors related to underrepresented populations. When testing our methods on image analytics, experiments demonstrate that TARA significantly or fully debiases baseline models while outperforming competing debiasing methods, e.g., with (% overall accuracy, % accuracy gap) = (78.75, 0.5) vs. the baseline method's score of (71.75, 10.5) for EyePACS, and (73.71, 11.82) vs. (69.08, 21.65) for CelebA. Furthermore, recognizing certain limitations in current metrics used for assessing debiasing performance, we propose novel conjunctive debiasing metrics. Our experiments also demonstrate the ability of these novel metrics in assessing the Pareto efficiency of the proposed methods.
翻译:这种方法使用一种双重战略,提供培训和代表,以缓解AI偏见的突出原因,其方法是:(a) 通过对抗性独立性,采用代表制学习方式的改变,以抑制数据代表从受保护因素中产生偏向性的依赖;(b) 通过智能增强,采用基因模型,对与代表人数不足的人口有关的敏感因素进行细微控制,从而解决造成偏向的数据不平衡问题。在测试我们的图像分析方法时,实验表明,TARA明显或完全贬低基线模型,而比相竞的偏向方法,例如,与EyePACS(71.75、10.5)相比,采用代表制代表制的改变(78.75、0.5)与基准方法的得分(71.75、10.5),以及CeebA(73.71、11.82)诉(69.08、21.65)。此外,我们建议采用新颖的分数,以显示这些新数在评估拟议方法的Pareto效率方面的能力。