Multi-criteria Rank-based Aggregation for Explainable AI

TL;DR

This paper introduces a multi-criteria rank-based aggregation method to improve the robustness and quality of explanations in explainable AI, balancing multiple metrics simultaneously.

Contribution

It proposes a novel multi-criteria rank-based weighted aggregation approach and rank-based evaluation metrics for explanations, addressing conflicting quality metrics in XAI.

Findings

The method produces more robust explanations across metrics.

TOPSIS and WSUM are identified as the best aggregation algorithms.

Experiments validate the effectiveness of the proposed approach.

Abstract

Explainability is crucial for improving the transparency of black-box machine learning models. With the advancement of explanation methods such as LIME and SHAP, various XAI performance metrics have been developed to evaluate the quality of explanations. However, different explainers can provide contrasting explanations for the same prediction, introducing trade-offs across conflicting quality metrics. Although available aggregation approaches improve robustness, reducing explanations' variability, very limited research employed a multi-criteria decision-making approach. To address this gap, this paper introduces a multi-criteria rank-based weighted aggregation method that balances multiple quality metrics simultaneously to produce an ensemble of explanation models. Furthermore, we propose rank-based versions of existing XAI metrics (complexity, faithfulness and stability) to better evaluate ranked feature importance explanations. Extensive experiments on publicly available datasets demonstrate the robustness of the proposed model across these metrics. Comparative analyses of various multi-criteria decision-making and rank aggregation algorithms showed that TOPSIS and WSUM are the best candidates for this use case.