Fighting the disagreement in Explainable Machine Learning with consensus

TL;DR

This paper evaluates six consensus functions for explaining machine learning models, demonstrating that a new proposed function offers more consistent, fair, and accurate explanations across synthetic datasets with known rules.

Contribution

The paper introduces and evaluates a new consensus function that improves the consistency and fairness of explanations in explainable machine learning.

Findings

The proposed consensus function outperforms others in fairness.

It provides more consistent explanations across models.

The function yields more accurate interpretability results.

Abstract

Machine learning (ML) models are often valued by the accuracy of their predictions. However, in some areas of science, the inner workings of models are as relevant as their accuracy. To understand how ML models work internally, the use of interpretability algorithms is the preferred option. Unfortunately, despite the diversity of algorithms available, they often disagree in explaining a model, leading to contradictory explanations. To cope with this issue, consensus functions can be applied once the models have been explained. Nevertheless, the problem is not completely solved because the final result will depend on the selected consensus function and other factors. In this paper, six consensus functions have been evaluated for the explanation of five ML models. The models were previously trained on four synthetic datasets whose internal rules were known in advance. The models were then explained with model-agnostic local and global interpretability algorithms. Finally, consensus was calculated with six different functions, including one developed by the authors. The results demonstrated that the proposed function is fairer than the others and provides more consistent and accurate explanations.