From Correlation to Causation: Formalizing Interpretable Machine Learning as a Statistical Process

TL;DR

This paper formalizes interpretable machine learning as a statistical process, clarifying its role in safety-critical applications and distinguishing it from classical statistics to enhance trust and adoption.

Contribution

It introduces a formal statistical framework for IML, connecting it with classical statistics and proposing key questions for its development in safety-critical domains.

Findings

Interpretable ML can be viewed as a statistical process.

Three key questions are crucial for IML's success in safety-critical settings.

The formalization aids in distinguishing IML from classical statistics.

Abstract

Explainable AI (XAI) is a necessity in safety-critical systems such as in clinical diagnostics due to a high risk for fatal decisions. Currently, however, XAI resembles a loose collection of methods rather than a well-defined process. In this work, we elaborate on conceptual similarities between the largest subgroup of XAI, interpretable machine learning (IML), and classical statistics. Based on these similarities, we present a formalization of IML along the lines of a statistical process. Adopting this statistical view allows us to interpret machine learning models and IML methods as sophisticated statistical tools. Based on this interpretation, we infer three key questions, which we identify as crucial for the success and adoption of IML in safety-critical settings. By formulating these questions, we further aim to spark a discussion about what distinguishes IML from classical statistics and what our perspective implies for the future of the field.