| Autor: |
Quinzan, Francesco, Casolo, Cecilia, Muandet, Krikamol, Luo, Yucen, Kilbertus, Niki |
| Rok vydání: |
2022 |
| Předmět: |
|
| Druh dokumentu: |
Working Paper |
| Popis: |
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. |
| Databáze: |
arXiv |
| Externí odkaz: |
|
