Modeling and Discovering Direct Causes for Predictive Models

We introduce a causal modeling framework that captures the input-output behavior of predictive models (e.g., machine learning models). The framework enables us to identify features that directly cause the predictions, which has broad implications for data collection and model evaluation. We then pre...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Proceedings of the International Florida Artificial Intelligence Research Society Conference Jg. 38; H. 1
Hauptverfasser: Chen, Yizuo, Bhatia, Amit
Format: Journal Article
Sprache:Englisch
Veröffentlicht: LibraryPress@UF 14.05.2025
Schlagworte:
causal models
Causality
explainability
ISSN:2334-0754, 2334-0762
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:We introduce a causal modeling framework that captures the input-output behavior of predictive models (e.g., machine learning models). The framework enables us to identify features that directly cause the predictions, which has broad implications for data collection and model evaluation. We then present sound and complete algorithms for discovering direct causes (from data) under some assumptions. Furthermore, we propose a novel independence rule that can be integrated with the algorithms to accelerate the discovery process as we demonstrate both theoretically and empirically.
ISSN:2334-0754
2334-0762
DOI:10.32473/flairs.38.1.139003