Startseite
English
Erweiterte Suche
Durchblättern nach ...
Publikationen im Überblick
Ansprechpartner
Hilfe
Postprint
 |
|
möglich sobald bei der ZB eingereicht worden ist.
Learning counterfactually invariant predictors.
Trans. Machine Learn. Res. 2024, accepted (2024)
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.
Weitere Metriken?
Zusatzinfos bearbeiten
[➜Einloggen]
Publikationstyp
Artikel: Journalartikel
Dokumenttyp
Wissenschaftlicher Artikel
ISSN (print) / ISBN
2835-8856
e-ISSN
2835-8856
Zeitschrift
Transactions on Machine Learning Research
Quellenangaben
Band: 2024
Verlag
Journal of Machine Learning Research Inc.
Nichtpatentliteratur
Publikationen
Begutachtungsstatus
Peer reviewed