Rethinking Counterfactual Data Augmentation Under Confounding

CoRR(2023)

引用 0|浏览25
暂无评分
摘要
Counterfactual data augmentation has recently emerged as a method to mitigate confounding biases in the training data for a machine learning model. These biases, such as spurious correlations, arise due to various observed and unobserved confounding variables in the data generation process. In this paper, we formally analyze how confounding biases impact downstream classifiers and present a causal viewpoint to the solutions based on counterfactual data augmentation. We explore how removing confounding biases serves as a means to learn invariant features, ultimately aiding in generalization beyond the observed data distribution. Additionally, we present a straightforward yet powerful algorithm for generating counterfactual images, which effectively mitigates the influence of confounding effects on downstream classifiers. Through experiments on MNIST variants and the CelebA datasets, we demonstrate the effectiveness and practicality of our approach.
更多
查看译文
关键词
counterfactual data augmentation
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要