Sampling - Variational Auto Encoder - Ensemble: In the Quest of Explainable Artificial Intelligence

TL;DR

This paper introduces SVEAD, a hybrid framework combining Sampling, Variational Auto Encoders, and Ensemble methods with SHAP for improved and explainable anomaly detection in imbalanced classification tasks.

Contribution

It presents a novel empirical framework integrating VAE, ensemble stacking, and SHAP to enhance model performance and interpretability in XAI applications.

Findings

Combining ensemble stacking, VAE, and SHAP improves model accuracy.

The framework provides clear explanations of model decisions.

Enhanced interpretability with SHAP, Permutation Importance, and ICE.

Abstract

Explainable Artificial Intelligence (XAI) models have recently attracted a great deal of interest from a variety of application sectors. Despite significant developments in this area, there are still no standardized methods or approaches for understanding AI model outputs. A systematic and cohesive framework is also increasingly necessary to incorporate new techniques like discriminative and generative models to close the gap. This paper contributes to the discourse on XAI by presenting an empirical evaluation based on a novel framework: Sampling - Variational Auto Encoder (VAE) - Ensemble Anomaly Detection (SVEAD). It is a hybrid architecture where VAE combined with ensemble stacking and SHapley Additive exPlanations are used for imbalanced classification. The finding reveals that combining ensemble stacking, VAE, and SHAP can. not only lead to better model performance but also provide an easily explainable framework. This work has used SHAP combined with Permutation Importance and Individual Conditional Expectations to create a powerful interpretability of the model. The finding has an important implication in the real world, where the need for XAI is paramount to boost confidence in AI applications.