论文标题
删除虚假特征会损害准确性，并影响群体不成比例
Removing Spurious Features can Hurt Accuracy and Affect Groups Disproportionately
论文作者
论文摘要
虚假特征的存在干扰了获得在人群中许多群体中表现良好的强大模型的目的。一种自然的补救措施是从模型中删除虚假特征。但是，在这项工作中，我们表明，由于过度参数化模型的电感偏差，删除虚假特征可以降低准确性。我们彻底表征了伪特征的去除如何影响无噪声过度参数线性回归中不同组（更一般的测试分布）的准确性。此外，我们表明，即使在平衡的数据集中，删除伪造功能也可以降低准确性 - 每个目标与每个虚假特征平均共同相关；它可以无意间使模型更容易受到其他虚假特征的影响。最后，我们表明强大的自我训练可以消除虚假特征而不会影响整体准确性。关于毒性症状 - 二甲基蛋白和Celeba数据集的实验表明，我们的结果在非线性模型中。
The presence of spurious features interferes with the goal of obtaining robust models that perform well across many groups within the population. A natural remedy is to remove spurious features from the model. However, in this work we show that removal of spurious features can decrease accuracy due to the inductive biases of overparameterized models. We completely characterize how the removal of spurious features affects accuracy across different groups (more generally, test distributions) in noiseless overparameterized linear regression. In addition, we show that removal of spurious feature can decrease the accuracy even in balanced datasets -- each target co-occurs equally with each spurious feature; and it can inadvertently make the model more susceptible to other spurious features. Finally, we show that robust self-training can remove spurious features without affecting the overall accuracy. Experiments on the Toxic-Comment-Detectoin and CelebA datasets show that our results hold in non-linear models.
