论文标题
解决多数的暴政的对比例子
Contrastive Examples for Addressing the Tyranny of the Majority
论文作者
论文摘要
计算机视觉算法，例如为了识别面部，偏爱培训数据中更好代表的个人群体。这是由于分类器必须进行的概括而发生的。拟合多数组更简单，因为这种拟合对于总体错误更为重要。我们建议创建一个平衡的培训数据集，该数据集由原始数据集以及新的数据点组成，其中小组成员是干预的，少数群体将成为多数，反之亦然。我们表明，当前的生成对抗网络是学习这些数据点的强大工具，称为对比度示例。我们在表格数据以及图像数据（面部数据集中的celeba和多样性）上实验了均衡的赔率偏差度量。对比的例子使我们能够公开小组成员与其他看似中立的特征之间的相关性。每当有因果图可用时，我们都可以将这些对比示例放在反事实的角度。
Computer vision algorithms, e.g. for face recognition, favour groups of individuals that are better represented in the training data. This happens because of the generalization that classifiers have to make. It is simpler to fit the majority groups as this fit is more important to overall error. We propose to create a balanced training dataset, consisting of the original dataset plus new data points in which the group memberships are intervened, minorities become majorities and vice versa. We show that current generative adversarial networks are a powerful tool for learning these data points, called contrastive examples. We experiment with the equalized odds bias measure on tabular data as well as image data (CelebA and Diversity in Faces datasets). Contrastive examples allow us to expose correlations between group membership and other seemingly neutral features. Whenever a causal graph is available, we can put those contrastive examples in the perspective of counterfactuals.
