Strategies to exploit XAI to improve classification systems

TL;DR

This paper investigates how explainable AI methods, particularly Integrated Gradients, can be exploited to enhance the performance of classification models, demonstrating empirical improvements on multiple datasets.

Contribution

It introduces and empirically evaluates strategies to leverage XAI explanations for improving classification accuracy, a less explored aspect of XAI research.

Findings

Integrated Gradients explanations can be used to improve classification performance.

Strategies based on XAI explanations show empirical gains on datasets.

XAI methods can be exploited beyond interpretability to enhance models.

Abstract

Explainable Artificial Intelligence (XAI) aims to provide insights into the decision-making process of AI models, allowing users to understand their results beyond their decisions. A significant goal of XAI is to improve the performance of AI models by providing explanations for their decision-making processes. However, most XAI literature focuses on how to explain an AI system, while less attention has been given to how XAI methods can be exploited to improve an AI system. In this work, a set of well-known XAI methods typically used with Machine Learning (ML) classification tasks are investigated to verify if they can be exploited, not just to provide explanations but also to improve the performance of the model itself. To this aim, two strategies to use the explanation to improve a classification system are reported and empirically evaluated on three datasets: Fashion-MNIST, CIFAR10, and STL10. Results suggest that explanations built by Integrated Gradients highlight input features that can be effectively used to improve classification performance.