Explainable Artificial Intelligence for Dependent Features: Additive Effects of Collinearity
This addresses the issue of unrealistic feature independence assumptions in XAI for practitioners needing reliable explanations in real-world applications, though it is an incremental improvement focused on a specific bottleneck.
The paper tackles the problem of collinearity in explainable AI (XAI) methods, which assume feature independence, by proposing the Additive Effects of Collinearity (AEC) method to account for collinearity when modeling feature effects, and results show it is more robust and stable compared to state-of-the-art XAI methods.
Explainable Artificial Intelligence (XAI) emerged to reveal the internal mechanism of machine learning models and how the features affect the prediction outcome. Collinearity is one of the big issues that XAI methods face when identifying the most informative features in the model. Current XAI approaches assume the features in the models are independent and calculate the effect of each feature toward model prediction independently from the rest of the features. However, such assumption is not realistic in real life applications. We propose an Additive Effects of Collinearity (AEC) as a novel XAI method that aim to considers the collinearity issue when it models the effect of each feature in the model on the outcome. AEC is based on the idea of dividing multivariate models into several univariate models in order to examine their impact on each other and consequently on the outcome. The proposed method is implemented using simulated and real data to validate its efficiency comparing with the a state of arts XAI method. The results indicate that AEC is more robust and stable against the impact of collinearity when it explains AI models compared with the state of arts XAI method.