Go to AAAI 2025 Workshop AICT homepageModeling and Discovering Direct Causes for Predictive Models
Keywords: Causal Modeling, Direct Causes, Predictive Model
TL;DR: We introduce a causal modeling framework to capture the behavior of predictive models and propose methods for finding direct causes of the predictions.
Abstract: We introduce a causal modeling framework that captures the input-output behavior of predictive models (e.g., machine learning models) by representing it using causal graphs. The framework enables us to define and identify features that directly cause the predictions, which has broad implications for data collection and model evaluation. We show two assumptions under which the direct causes can be discovered from data, one of which further simplifies the discovery process. In addition to providing sound and complete algorithms, we propose an optimization technique based on an independence rule that can be integrated with the algorithms to speed up the discovery process both theoretically and empirically.
Submission Number: 12
Loading