Linking Model Intervention to Causal Interpretation in Model Explanation

• Published in: arXiv.org 2024-10
• Main Authors: Debo Cheng, Xu, Ziqi, Li, Jiuyong, Liu, Lin, Yu, Kui, Le, Thuc Duy, Liu, Jixue
• Format: Article
• Language: English
• Subjects: Machine learning; Synthetic data
• ISSN: 2331-8422

Intervention intuition is often used in model explanation where the intervention effect of a feature on the outcome is quantified by the difference of a model prediction when the feature value is changed from the current value to the baseline value. Such a model intervention effect of a feature is inherently association. In this paper, we will study the conditions when an intuitive model intervention effect has a causal interpretation, i.e., when it indicates whether a feature is a direct cause of the outcome. This work links the model intervention effect to the causal interpretation of a model. Such an interpretation capability is important since it indicates whether a machine learning model is trustworthy to domain experts. The conditions also reveal the limitations of using a model intervention effect for causal interpretation in an environment with unobserved features. Experiments on semi-synthetic datasets have been conducted to validate theorems and show the potential for using the model intervention effect for model interpretation.