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...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings of the International Florida Artificial Intelligence Research Society Conference Vol. 38; no. 1
Main Authors: Chen, Yizuo, Bhatia, Amit
Format: Journal Article
Language:English
Published: LibraryPress@UF 14.05.2025
Subjects:
causal models
Causality
explainability
ISSN:2334-0754, 2334-0762
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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