Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Karolczak, Jacek, Stefanowski, Jerzy
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2605.21646
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911703400185856
author Karolczak, Jacek
Stefanowski, Jerzy
author_facet Karolczak, Jacek
Stefanowski, Jerzy
contents 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 \textit{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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_21646
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Alike Parts: A Feature-Informed Approach to Local and Global Prototype Explanations
Karolczak, Jacek
Stefanowski, Jerzy
Machine Learning
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 \textit{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.
title Alike Parts: A Feature-Informed Approach to Local and Global Prototype Explanations
topic Machine Learning
url https://arxiv.org/abs/2605.21646