Modeling and Discovering Direct Causes for Predictive Models
DOI:
https://doi.org/10.32473/flairs.38.1.139003Keywords:
Causality, causal models, explainabilityAbstract
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.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Yizuo Chen, Amit Bhatia

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.