DeepAI AI Chat
Log In Sign Up

Explanatory causal effects for model agnostic explanations

by   Jiuyong Li, et al.

This paper studies the problem of estimating the contributions of features to the prediction of a specific instance by a machine learning model and the overall contribution of a feature to the model. The causal effect of a feature (variable) on the predicted outcome reflects the contribution of the feature to a prediction very well. A challenge is that most existing causal effects cannot be estimated from data without a known causal graph. In this paper, we define an explanatory causal effect based on a hypothetical ideal experiment. The definition brings several benefits to model agnostic explanations. First, explanations are transparent and have causal meanings. Second, the explanatory causal effect estimation can be data driven. Third, the causal effects provide both a local explanation for a specific prediction and a global explanation showing the overall importance of a feature in a predictive model. We further propose a method using individual and combined variables based on explanatory causal effects for explanations. We show the definition and the method work with experiments on some real-world data sets.


Linking a predictive model to causal effect estimation

A predictive model makes outcome predictions based on some given feature...

CXPlain: Causal Explanations for Model Interpretation under Uncertainty

Feature importance estimates that inform users about the degree to which...

Efficient SAGE Estimation via Causal Structure Learning

The Shapley Additive Global Importance (SAGE) value is a theoretically a...

Estimation of interventional effects of features on prediction

The interpretability of prediction mechanisms with respect to the underl...

DALE: Differential Accumulated Local Effects for efficient and accurate global explanations

Accumulated Local Effect (ALE) is a method for accurately estimating fea...

Explaining Visual Models by Causal Attribution

Model explanations based on pure observational data cannot compute the e...