Learning Counterfactually Invariant Predictors

Francesco Quinzan, Cecilia Casolo, Krikamol Muandet, Yucen Luo, Niki Kilbertus

Primary Area: causal reasoning

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: Causality, Counterfactual Invariance

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

TL;DR: We propose a model-agnostic framework building on a kernel-based conditional dependence measure for learning counterfactually invariant predictors.

Abstract: Notions of counterfactual invariance have proven essential for predictors that are fair, robust, and generalizable in the real world. We propose simple graphical criteria that yield a sufficient condition for a predictor to be counterfactually invariant in terms of (conditional independence in) the observational distribution. Any predictor that satisfies our criterion is provably counterfactually invariant. In order to learn such predictors, we propose a model-agnostic framework, called Counterfactual Invariance Prediction (CIP), building on a kernel-based conditional dependence measure called Hilbert-Schmidt Conditional Independence Criterion (HSCIC). 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.real-world dataset.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 5832