Towards A Rigorous Science of Interpretable Machine Learning

TL;DR

This paper discusses the need for a clear, rigorous scientific framework for interpretability in machine learning, proposing definitions, evaluation taxonomy, and highlighting open research questions.

Contribution

It provides a formal definition of interpretability, a taxonomy for evaluation, and outlines open questions to advance scientific understanding in the field.

Findings

Defines interpretability and its necessity

Proposes a taxonomy for evaluating interpretability

Identifies open research questions

Abstract

As machine learning systems become ubiquitous, there has been a surge of interest in interpretable machine learning: systems that provide explanation for their outputs. These explanations are often used to qualitatively assess other criteria such as safety or non-discrimination. However, despite the interest in interpretability, there is very little consensus on what interpretable machine learning is and how it should be measured. In this position paper, we first define interpretability and describe when interpretability is needed (and when it is not). Next, we suggest a taxonomy for rigorous evaluation and expose open questions towards a more rigorous science of interpretable machine learning.