X-SHIELD: Regularization for eXplainable Artificial Intelligence

TL;DR

X-SHIELD introduces a novel regularization method that enhances both the explainability and performance of AI models by selectively hiding input features based on explanations, validated through experiments on benchmark datasets.

Contribution

The paper proposes X-SHIELD, a new regularization technique that integrates explanation-driven feature hiding to improve model explainability and accuracy simultaneously.

Findings

X-SHIELD improves model performance on benchmark datasets.

X-SHIELD enhances model explainability.

Experimental results validate the effectiveness of the regularization.

Abstract

As artificial intelligence systems become integral across domains, the demand for explainability grows, the called eXplainable artificial intelligence (XAI). Existing efforts primarily focus on generating and evaluating explanations for black-box models while a critical gap in directly enhancing models remains through these evaluations. It is important to consider the potential of this explanation process to improve model quality with a feedback on training as well. XAI may be used to improve model performance while boosting its explainability. Under this view, this paper introduces Transformation - Selective Hidden Input Evaluation for Learning Dynamics (T-SHIELD), a regularization family designed to improve model quality by hiding features of input, forcing the model to generalize without those features. Within this family, we propose the XAI - SHIELD(X-SHIELD), a regularization for explainable artificial intelligence, which uses explanations to select specific features to hide. In contrast to conventional approaches, X-SHIELD regularization seamlessly integrates into the objective function enhancing model explainability while also improving performance. Experimental validation on benchmark datasets underscores X-SHIELD's effectiveness in improving performance and overall explainability. The improvement is validated through experiments comparing models with and without the X-SHIELD regularization, with further analysis exploring the rationale behind its design choices. This establishes X-SHIELD regularization as a promising pathway for developing reliable artificial intelligence regularization.