Characterizing the contribution of dependent features in XAI methods
This addresses a limitation in interpretability for users of XAI tools, but it is incremental as it modifies existing methods rather than introducing a new paradigm.
The authors tackled the problem that existing XAI methods assume feature independence, which can undermine the robustness of feature importance rankings. They proposed a model-agnostic proxy to adjust XAI outcomes for feature dependencies, though no concrete performance numbers were provided.
Explainable Artificial Intelligence (XAI) provides tools to help understanding how the machine learning models work and reach a specific outcome. It helps to increase the interpretability of models and makes the models more trustworthy and transparent. In this context, many XAI methods were proposed being SHAP and LIME the most popular. However, the proposed methods assume that used predictors in the machine learning models are independent which in general is not necessarily true. Such assumption casts shadows on the robustness of the XAI outcomes such as the list of informative predictors. Here, we propose a simple, yet useful proxy that modifies the outcome of any XAI feature ranking method allowing to account for the dependency among the predictors. The proposed approach has the advantage of being model-agnostic as well as simple to calculate the impact of each predictor in the model in presence of collinearity.