Meta-evaluating stability measures: MAX-Senstivity & AVG-Sensitivity

Abstract

The use of eXplainable Artificial Intelligence (XAI) systems has introduced a set of challenges that need resolution. The XAI robustness, or stability, has been one of the goals of the community from its beginning. Multiple authors have proposed evaluating this feature using objective evaluation measures. Nonetheless, many questions remain. With this work, we propose a novel approach to meta-evaluate these metrics, i.e. analyze the correctness of the evaluators. We propose two new tests that allowed us to evaluate two different stability measures: AVG-Sensitiviy and MAX-Senstivity. We tested their reliability in the presence of perfect and robust explanations, generated with a Decision Tree; as well as completely random explanations and prediction. The metrics results showed their incapacity of identify as erroneous the random explanations, highlighting their overall unreliability.

References in corpus (5)

• Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks
• Explainable artificial intelligence (XAI) in deep learning-based medical image analysis
• Ground Truth Evaluation of Neural Network Explanations with CLEVR-XAI
• Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyond
• Opening the Black-Box: A Systematic Review on Explainable AI in Remote Sensing