Okarma, Krzysztof - ed. ; Skrzypczyński, Piotr - ed. ; Stefanowski, Jerzy - ed.
Prototype-based explanations offer an intuitive, example-based approach to support the interpretability of machine learning black box classifiers but often lack feature-level granularity. We introduce a framework that integrates feature importance at two levels to address this gap. First, for local explanations, we propose alike parts - a method that uses feature importance scores to highlight the most relevant, shared feature subsets between a classified instance and its nearest prototype, guiding user attention. ; Second, we augment the global prototype selection objective function with a feature importance term to actively promote diversity in the feature attributions of the selected prototypes. Experiments on six benchmark datasets show that this augmented selection process maintains or, in some cases, increases the prediction fidelity of the surrogate model, suggesting that feature diversity does not compromise model fidelity.
Zielona Góra: Uniwersytet Zielonogórski
AMCS, volume 36, number 3 (2026)
Biblioteka Uniwersytetu Zielonogórskiego
Nov 6, 2026
Nov 6, 2026
0
https://zbc.uz.zgora.pl/repozytorium/publication/115172
| Edition name | Date |
|---|---|
| Alike parts: a feature-informed approach to local and global prototype explanations | Nov 6, 2026 |
Stępka, Ignacy Lango, Mateusz Stefanowski, Jerzy Korbicz, Józef (1951- ) - red. Uciński, Dariusz - red.
Wichrowski, Filip Ostrowski, Marcin Boratyn, Marta Kaczmarek-Majer, Katarzyna Korbicz, Józef (1951- ) - red. Uciński, Dariusz - red.
Stefanowski, Jerzy Krawiec, Krzysztof Wrembel, Robert Stefanowski, Jerzy - ed. Krawiec, Krzysztof - ed. Wrembel, Robert - ed.
Janicka, Małgorzata Lango, Mateusz Stefanowski, Jerzy Clempner, Julio B. - ed. Ikonen, Enso - ed. Kurdyukov, Alexander P. - ed.