Interpretability and Explainability: A Machine Learning Zoo Mini-tour

TL;DR

This paper reviews the distinctions and developments in interpretability and explainability in machine learning, highlighting recent advances especially in deep learning, and aims to guide researchers beyond traditional models.

Contribution

It clarifies the divide between interpretability and explainability, illustrating current research directions with concrete examples, serving as a primer for a broad machine learning audience.

Findings

Differentiate interpretability and explainability with concrete examples

Highlight recent shifts towards deep learning methods

Provide insights into state-of-the-art techniques

Abstract

In this review, we examine the problem of designing interpretable and explainable machine learning models. Interpretability and explainability lie at the core of many machine learning and statistical applications in medicine, economics, law, and natural sciences. Although interpretability and explainability have escaped a clear universal definition, many techniques motivated by these properties have been developed over the recent 30 years with the focus currently shifting towards deep learning methods. In this review, we emphasise the divide between interpretability and explainability and illustrate these two different research directions with concrete examples of the state-of-the-art. The review is intended for a general machine learning audience with interest in exploring the problems of interpretation and explanation beyond logistic regression or random forest variable importance. This work is not an exhaustive literature survey, but rather a primer focusing selectively on certain lines of research which the authors found interesting or informative.