Pixel-Based Clustering for Local Interpretable Model-Agnostic Explanations

doi:10.2478/jaiscr-2025-0013

Pixel-Based Clustering for Local Interpretable Model-Agnostic Explanations

2025-07-01

0

OA

AI

DOI：10.2478/jaiscr-2025-0013

原文链接

原文求助

摘要

En 中文

To enhance the interpretability of black-box machine learning, model-agnostic explanations have become a focal point of interest. This paper introduces Pixel-based Local Interpretable Model-agnostic Explanations (PLIME), a method that generates perturbation samples via pixel clustering to derive raw explanations. Through iterative refinement, it reduces the number of features, culminating in an optimal feature set that best predicts the model's score. PLIME increases the relevance of features associated with correct predictions in the explanations. A comprehensive evaluation of PLIME is conducted against LIME and SHAP, focusing on faithfulness, stability, and minimality. Additionally, the predictions from both PLIME and LIME are utilized in Random Input Sampling Explanations (RISE) to compare minimality. The results demonstrate PLIME's significant advantages in stability, faithfulness, and minimality.

Keyword:

interpretability

explainable artificial intelligence

model-agnostic explanations

black-box model

Pixel-Based Clustering for Local Interpretable Model-Agnostic Explanations

摘要

期刊

机构

引用论文