Combination of Weak Learners eXplanations to Improve Random Forest eXplicability Robustness
This work addresses robustness issues in explainable AI for ensemble methods, offering an incremental improvement to enhance reliability in domains like healthcare or finance.
The paper tackles the problem of explanation robustness in XAI for ensemble methods, proposing a combination of weak learner explanations via discriminative averaging to improve robustness, with successful results measured quantitatively using SHAP and Random Forest.
The notion of robustness in XAI refers to the observed variations in the explanation of the prediction of a learned model with respect to changes in the input leading to that prediction. Intuitively, if the input being explained is modified slightly subtly enough so as to not change the prediction of the model too much, then we would expect that the explanation provided for that new input does not change much either. We argue that a combination through discriminative averaging of ensembles weak learners explanations can improve the robustness of explanations in ensemble methods.This approach has been implemented and tested with post-hoc SHAP method and Random Forest ensemble with successful results. The improvements obtained have been measured quantitatively and some insights into the explicability robustness in ensemble methods are presented.