Learning Counterfactually Invariant Predictors
Notions of counterfactual invariance (CI) have proven essential for predictors that are fair, robust, and generalizable in the real world. We propose graphical criteria that yield a sufficient condition for a predictor to be counterfactually invariant in terms of a conditional independence in the observational distribution. In order to learn such predictors, we propose a model-agnostic framework, called Counterfactually Invariant Prediction (CIP), building on the Hilbert-Schmidt Conditional Independence Criterion (HSCIC), a kernel-based conditional dependence measure. Our experimental results demonstrate the effectiveness of CIP in enforcing counterfactual invariance across various simulated and real-world datasets including scalar and multi-variate settings.
Code (2)
Tasks
counterfactualObject RecognitionSimilar Papers 제목 키워드 기반
Counterfactually Fair Conformal Prediction
While counterfactual fairness of point predictors is well studied, its extension to prediction sets--central to fair decision-making under uncertainty--remains underexplored. On the other hand, conformal prediction (CP) …
Asymmetry Learning for Counterfactually-invariant Classification in OOD Tasks
Generalizing from observed to new related environments (out-of-distribution) is central to the reliability of classifiers. However, most classifiers fail to predict label $Y$ from input $X$ when the change in environment…
ClassificationImproving Out-of-Distribution Robustness via Selective Augmentation
Machine learning algorithms typically assume that training and test examples are drawn from the same distribution. However, distribution shift is a common problem in real-world applications and can cause models to perfor…
An Investigation of the (In)effectiveness of Counterfactually Augmented Data
While pretrained language models achieve excellent performance on natural language understanding benchmarks, they tend to rely on spurious correlations and generalize poorly to out-of-distribution (OOD) data. Recent work…
DiversityNatural Language UnderstandingAn Investigation of the (In)effectiveness of Counterfactually Augmented Data
While pretrained language models achieve excellent performance on natural language understanding benchmarks, they tend to rely on spurious correlations and generalize poorly to out-of-distribution (OOD) data. Recent work…
DiversityNatural Language Understanding