Mechanistic Interpretation of Machine Learning Inference: A Fuzzy Feature Importance Fusion Approach

TL;DR

This paper introduces a fuzzy data fusion approach to improve the reliability and interpretability of feature importance explanations in machine learning models, addressing limitations of existing crisp fusion methods.

Contribution

It proposes a novel fuzzy fusion technique for combining feature importance quantifiers from multiple models, enhancing explanation robustness and comprehensibility.

Findings

Fuzzy fusion improves explanation reliability over crisp methods.

Fuzzy approach retains more information and context.

Enhanced interpretability for end-users and decision makers.

Abstract

With the widespread use of machine learning to support decision-making, it is increasingly important to verify and understand the reasons why a particular output is produced. Although post-training feature importance approaches assist this interpretation, there is an overall lack of consensus regarding how feature importance should be quantified, making explanations of model predictions unreliable. In addition, many of these explanations depend on the specific machine learning approach employed and on the subset of data used when calculating feature importance. A possible solution to improve the reliability of explanations is to combine results from multiple feature importance quantifiers from different machine learning approaches coupled with re-sampling. Current state-of-the-art ensemble feature importance fusion uses crisp techniques to fuse results from different approaches. There is, however, significant loss of information as these approaches are not context-aware and reduce several quantifiers to a single crisp output. More importantly, their representation of 'importance' as coefficients is misleading and incomprehensible to end-users and decision makers. Here we show how the use of fuzzy data fusion methods can overcome some of the important limitations of crisp fusion methods.