T-Explainer: A Model-Agnostic Explainability Framework Based on Gradients

doi:10.1109/MIS.2025.3564330

T-Explainer: A Model-Agnostic Explainability Framework Based on Gradients

0

PRE

AI

DOI：10.1109/MIS.2025.3564330

Original

Original request for help

Save

Abstract

En 中文

Modern learning models, while powerful, often exhibit a complexity level that renders them opaque black boxes, lacking transparency and hindering our understanding of their decision-making processes. Opacity challenges the practical application of machine learning, especially in critical domains requiring informed decisions. Explainable artificial intelligence (XAI) addresses that challenge, unraveling the complexity of black boxes by providing explanations. Feature attribution/importance XAI stands out for its ability to delineate the significance of input features in predictions. However, most attribution methods have limitations, such as instability, when divergent explanations result from similar or the same instance. This work introduces T-Explainer, a novel additive attribution explainer based on the Taylor expansion that offers desirable properties, such as local accuracy and consistency. We demonstrate T-Explainer’s effectiveness and stability over multiple runs in quantitative benchmark experiments against well-known attribution methods. Additionally, we provide several tools to evaluate and visualize explanations, turning T-Explainer into a comprehensive XAI framework.

Keywords:

Computational modeling

Mathematical models

Artificial intelligence

Accuracy

Predictive models

Explainable AI

Context modeling

Taylor series

Perturbation methods

Learning systems

Gradient methods

Closed box

Decision making

Benchmark testing

T-Explainer: A Model-Agnostic Explainability Framework Based on Gradients

Abstract

Journal

Organization