MCIR: A Feature Dependence-Aware Explainability Method with Reliability Guarantees
Modern machine-learning models often contain strongly dependent or redundant features, making feature attribution difficult because shared predictive information can be distributed across correlated predictors. Existing methods such as SHAP, LIME, HSIC, MI/CMI, and SAGE may therefore produce unstable rankings under mul...
Poushali Sengupta, S. Maharjan, Frank Eliassen et al.
· 0 citations