论文标题
公平：通过验证设置敏感属性，通过影响功能来提高深度学习的公平性
FairIF: Boosting Fairness in Deep Learning via Influence Functions with Validation Set Sensitive Attributes
论文作者
论文摘要
大多数公平的机器学习方法高度依赖于培训样本的敏感信息，或者需要对目标模型进行大规模修改，从而阻碍其实际应用。为了解决这个问题，我们提出了一种名为Fairif的两阶段培训算法。它最大程度地减少了重新加权数据集（第二阶段）的损失，在该数据集（第二阶段）计算样本权重以平衡不同人口组（第一阶段）的模型性能。 Fairif可以应用于通过随机梯度下降训练的各种模型，而无需更改模型，而仅需要在小验证集中进行小组注释来计算样品重量。从理论上讲，我们表明，在分类环境中，可以通过使用权重训练来减轻不同群体之间的三个差异概念。关于合成数据集的实验表明，公平的模型可以针对各种类型的偏见具有更好的公平性权衡权衡；在现实世界数据集上，我们显示了公平的有效性和可扩展性。此外，正如预处理模型的实验所证明的那样，Fairif能够减轻预算模型的不公平问题而不会损害其性能。
Most fair machine learning methods either highly rely on the sensitive information of the training samples or require a large modification on the target models, which hinders their practical application. To address this issue, we propose a two-stage training algorithm named FAIRIF. It minimizes the loss over the reweighted data set (second stage) where the sample weights are computed to balance the model performance across different demographic groups (first stage). FAIRIF can be applied on a wide range of models trained by stochastic gradient descent without changing the model, while only requiring group annotations on a small validation set to compute sample weights. Theoretically, we show that, in the classification setting, three notions of disparity among different groups can be mitigated by training with the weights. Experiments on synthetic data sets demonstrate that FAIRIF yields models with better fairness-utility trade-offs against various types of bias; and on real-world data sets, we show the effectiveness and scalability of FAIRIF. Moreover, as evidenced by the experiments with pretrained models, FAIRIF is able to alleviate the unfairness issue of pretrained models without hurting their performance.
