Open access
Jul 2026
iAdditive: fast and fair Shapley-inspired feature attribution for correlated features
iAdditive is presented, a model-agnostic approach that promotes fairness by grouping highly correlated or redundant features through group-level attribution semantics and improves efficiency via a dynamic coalition heuristic inspired by additive explanation methods.
Abirami Gunasekaran, Min-Si Chen, Richard Hill et al.
· International Journal of Dat... · 0 citations