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...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Proceedings of the International Florida Artificial Intelligence Research Society Conference Ročník 38; číslo 1
Hlavní autoři: Chen, Yizuo, Bhatia, Amit
Médium: Journal Article
Jazyk:angličtina
Vydáno: LibraryPress@UF 14.05.2025
Témata:
causal models
Causality
explainability
ISSN:2334-0754, 2334-0762
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí: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