反事实规范化：使用因果机制主动解决数据集偏移并提高可靠性
Counterfactual Normalization: Proactively Addressing Dataset Shift and Improving Reliability Using Causal Mechanisms
摘要：
由于数据集的变化，预测模型可能无法从训练环境推广到部署环境，从而对模型的可靠性和下游决策的安全性构成威胁。我们不是使用来自目标分布的样本来反应性地纠正数据集偏移，而是使用与预测问题中的变量相关的因果机制的图形知识来主动删除不跨环境泛化的关系，即使这些关系可能依赖于未观察到的变量（违反“没有未观察到的混杂因素”假设）。为了实现这一点，我们识别具有统计影响的不稳定路径的变量，并将其从模型中删除。我们还用潜在的反事实变量来增强因果图，这些变量隔离了统计影响的不稳定路径，使我们能够保留否则会被删除的稳定路径。我们的实验表明，去除脆弱变量并使用潜变量估计值的模型传递得更好，尽管在训练域中有一些准确性损失，但在目标域中通常表现出色。
英文摘要：
Predictive models can fail to generalize from training to deployment environments because of dataset shift, posing a threat to model reliability and the safety of downstream decisions made in practice. Instead of using samples from the target distribution to reactively correct dataset shift, we use graphical knowledge of the causal mechanisms relating variables in a prediction problem to proactively remove relationships that do not generalize across environments, even when these relationships may depend on unobserved variables (violations of the "no unobserved confounders" assumption). To accomplish this, we identify variables with unstable paths of statistical influence and remove them from the model. We also augment the causal graph with latent counterfactual variables that isolate unstable paths of statistical influence, allowing us to retain stable paths that would otherwise be removed. Our experiments demonstrate that models that remove vulnerable variables and use estimates of the latent variables transfer better, often outperforming in the target domain despite some accuracy loss in the training domain.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
