Counterfactual Normalization: Proactively Addressing Dataset Shift and Improving Reliability Using Causal Mechanisms

By Adarsh Subbaswamy, Suchi Saria. 2018

27 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Safety, Robustness & Interpretability, Causal Inference & Discovery

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Safety, Robustness & Interpretability

In Causal Inference & Discovery

Citations in the corpus

Toward Causal Representation Learning (2021, background): “While it may be useful to automate certain decisions, an understanding of causality may be necessary to recommend treatment options that are personalized and reliable [3], [6], [31], [164], [201], [224], [242], [273].”
Towards Causal Representation Learning (2021, background): “While it may be useful to automate certain decisions, an understanding of causality may be necessary to recommend treatment options that are personalized and reliable [201, 242, 224, 273, 6, 3, 30, 165].”
Preventing Failures Due to Dataset Shift: Learning Predictive Models That Transport (2018, background): “This motivates the need for proactive approaches which anticipate and address the differences between training and deployment environments without using deployment data (Subbaswamy and Saria, 2018).”
Causally motivated shortcut removal using auxiliary labels (2021, methodology): “Similar to this work, Subbaswamy and Saria [2018] develop methods to create estimators that are stable across distribution shifts by appealing to causal DAGS and without requiring access to samples from the target distribution.”