Explainable Artificial Intelligence and Multicollinearity : A Mini Review of Current Approaches

TL;DR

This paper reviews current XAI approaches focusing on how they address multicollinearity issues, highlighting limitations and proposing future research directions.

Contribution

It provides the first focused review on handling multicollinearity within XAI methods, analyzing recent approaches and identifying gaps.

Findings

Seven relevant papers identified and analyzed

Current XAI methods have limitations with multicollinearity

Future research directions are suggested

Abstract

Explainable Artificial Intelligence (XAI) methods help to understand the internal mechanism of machine learning models and how they reach a specific decision or made a specific action. The list of informative features is one of the most common output of XAI methods. Multicollinearity is one of the big issue that should be considered when XAI generates the explanation in terms of the most informative features in an AI system. No review has been dedicated to investigate the current approaches to handle such significant issue. In this paper, we provide a review of the current state-of-the-art approaches in relation to the XAI in the context of recent advances in dealing with the multicollinearity issue. To do so, we searched in three repositories that are: Web of Science, Scopus and IEEE Xplore to find pertinent published papers. After excluding irrelevant papers, seven papers were considered in the review. In addition, we discuss the current XAI methods and their limitations in dealing with the multicollinearity and suggest future directions.