English

Learning Counterfactually Invariant Predictors

Machine Learning 2024-08-12 v4 Machine Learning

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}
}
R2 v1 2026-06-25T01:04:33.176Z