Learning Counterfactually Invariant Predictors
Abstract
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.
Keywords
Cite
@article{arxiv.2207.09768,
title = {Learning Counterfactually Invariant Predictors},
author = {Francesco Quinzan and Cecilia Casolo and Krikamol Muandet and Yucen Luo and Niki Kilbertus},
journal= {arXiv preprint arXiv:2207.09768},
year = {2024}
}