CAGE: Causality-Aware Shapley Value for Global Explanations

TL;DR

CAGE introduces a causality-aware method for global explanations in AI models, improving interpretability by incorporating causal relations into Shapley value calculations, leading to more faithful and intuitive feature importance explanations.

Contribution

The paper proposes a novel causally-aware sampling procedure for Shapley values, enhancing global explanations by integrating causal knowledge into feature importance assessments.

Findings

More intuitive explanations on synthetic data

More faithful explanations on real-world data

Improved interpretability over existing methods

Abstract

As Artificial Intelligence (AI) is having more influence on our everyday lives, it becomes important that AI-based decisions are transparent and explainable. As a consequence, the field of eXplainable AI (or XAI) has become popular in recent years. One way to explain AI models is to elucidate the predictive importance of the input features for the AI model in general, also referred to as global explanations. Inspired by cooperative game theory, Shapley values offer a convenient way for quantifying the feature importance as explanations. However many methods based on Shapley values are built on the assumption of feature independence and often overlook causal relations of the features which could impact their importance for the ML model. Inspired by studies of explanations at the local level, we propose CAGE (Causally-Aware Shapley Values for Global Explanations). In particular, we introduce a novel sampling procedure for out-coalition features that respects the causal relations of the input features. We derive a practical approach that incorporates causal knowledge into global explanation and offers the possibility to interpret the predictive feature importance considering their causal relation. We evaluate our method on synthetic data and real-world data. The explanations from our approach suggest that they are not only more intuitive but also more faithful compared to previous global explanation methods.