A New Technique for AI Explainability using Feature Association Map

TL;DR

This paper introduces FAMeX, a novel graph-theoretic explainability algorithm for AI that outperforms existing methods like PFI and SHAP in gauging feature importance.

Contribution

The paper presents FAMeX, a new feature association map-based algorithm that improves AI explainability by better capturing feature importance.

Findings

FAMeX outperforms PFI and SHAP in experiments.

FAMeX effectively gauges feature importance in classification tasks.

Experiments conducted on eight benchmark algorithms show promising results.

Abstract

Lack of transparency in AI systems poses challenges in critical real-life applications. It is important to be able to explain the decisions of an AI system to ensure trust on the system. Explainable AI (XAI) algorithms play a vital role in achieving this objective. In this paper, we are proposing a new algorithm for Explaining AI systems, FAMeX (Feature Association Map based eXplainability). The proposed algorithm is based on a graph-theoretic formulation of the feature set termed as Feature Association Map (FAM). The foundation of the modelling is based on association between features. The proposed FAMeX algorithm has been found to be better than the competing XAI algorithms - Permutation Feature Importance (PFI) and SHapley Additive exPlanations (SHAP). Experiments conducted with eight benchmark algorithms show that FAMeX is able to gauge feature importance in the context of classification better than the competing algorithms. This definitely shows that FAMeX is a promising algorithm in explaining the predictions from an AI system