AcME -- Accelerated Model-agnostic Explanations: Fast Whitening of the Machine-Learning Black Box

TL;DR

AcME is a fast, model-agnostic interpretability method that provides quick feature importance scores and what-if analysis for machine learning models, enabling real-time insights in decision support systems.

Contribution

This paper introduces AcME, a novel accelerated approach for model-agnostic explanations that significantly reduces computation time while maintaining explanation quality.

Findings

Achieved comparable explanation quality to SHAP

Dramatically reduced computational time

Provided consistent global and local visualizations

Abstract

In the context of human-in-the-loop Machine Learning applications, like Decision Support Systems, interpretability approaches should provide actionable insights without making the users wait. In this paper, we propose Accelerated Model-agnostic Explanations (AcME), an interpretability approach that quickly provides feature importance scores both at the global and the local level. AcME can be applied a posteriori to each regression or classification model. Not only does AcME compute feature ranking, but it also provides a what-if analysis tool to assess how changes in features values would affect model predictions. We evaluated the proposed approach on synthetic and real-world datasets, also in comparison with SHapley Additive exPlanations (SHAP), the approach we drew inspiration from, which is currently one of the state-of-the-art model-agnostic interpretability approaches. We achieved comparable results in terms of quality of produced explanations while reducing dramatically the computational time and providing consistent visualization for global and local interpretations. To foster research in this field, and for the sake of reproducibility, we also provide a repository with the code used for the experiments.