论文标题
盲人：无人口统计学的偏见消除
BLIND: Bias Removal With No Demographics
论文作者
论文摘要
对现实数据培训的模型往往会模仿和扩大社会偏见。减轻偏见的常见方法需要有关应减轻偏见类型的事先信息（例如，性别或种族偏见）以及与每个数据样本相关的社会群体。在这项工作中，我们引入了盲人，这是一种偏见删除的方法，而没有对数据集中的人口统计信息进行事先了解。在训练下游任务的模型时，Flind使用辅助模型来检测偏见的样品，该模型可以预测主要模型的成功，并在训练过程中降低了这些样本。在情感分类和职业分类任务中具有种族和性别偏见的实验表明，盲人会减轻社会偏见而不依赖昂贵的人口统计注释过程。我们的方法与需要人口统计信息甚至超过人口信息的其他方法具有竞争力。
Models trained on real-world data tend to imitate and amplify social biases. Common methods to mitigate biases require prior information on the types of biases that should be mitigated (e.g., gender or racial bias) and the social groups associated with each data sample. In this work, we introduce BLIND, a method for bias removal with no prior knowledge of the demographics in the dataset. While training a model on a downstream task, BLIND detects biased samples using an auxiliary model that predicts the main model's success, and down-weights those samples during the training process. Experiments with racial and gender biases in sentiment classification and occupation classification tasks demonstrate that BLIND mitigates social biases without relying on a costly demographic annotation process. Our method is competitive with other methods that require demographic information and sometimes even surpasses them.
