The Susceptibility of Example-Based Explainability Methods to Class Outliers

TL;DR

This paper investigates how class outliers affect the reliability of example-based explainability methods in machine learning, revealing their vulnerabilities and proposing evaluation metrics to improve robustness.

Contribution

It reformulates evaluation metrics for example-based explanations and introduces a new metric, distinguishability, to better assess method performance against class outliers.

Findings

Current methods are vulnerable to class outliers.

Existing metrics may not fully capture explainability quality.

Robust techniques are needed to handle class outliers effectively.

Abstract

This study explores the impact of class outliers on the effectiveness of example-based explainability methods for black-box machine learning models. We reformulate existing explainability evaluation metrics, such as correctness and relevance, specifically for example-based methods, and introduce a new metric, distinguishability. Using these metrics, we highlight the shortcomings of current example-based explainability methods, including those who attempt to suppress class outliers. We conduct experiments on two datasets, a text classification dataset and an image classification dataset, and evaluate the performance of four state-of-the-art explainability methods. Our findings underscore the need for robust techniques to tackle the challenges posed by class outliers.