Beyond Model Interpretability: Socio-Structural Explanations in Machine Learning

TL;DR

This paper introduces sociostructural explanations as a new interpretability approach that considers social structures influencing machine learning outputs, demonstrated through a racially biased healthcare algorithm.

Contribution

It proposes sociostructural explanations as a novel interpretability framework that incorporates social context into understanding machine learning outputs.

Findings

Sociostructural explanations reveal social influences on model outputs.

Application to healthcare shows social structures impact algorithm bias.

Highlights need for transparency beyond technical model interpretability.

Abstract

What is it to interpret the outputs of an opaque machine learning model. One approach is to develop interpretable machine learning techniques. These techniques aim to show how machine learning models function by providing either model centric local or global explanations, which can be based on mechanistic interpretations revealing the inner working mechanisms of models or nonmechanistic approximations showing input feature output data relationships. In this paper, we draw on social philosophy to argue that interpreting machine learning outputs in certain normatively salient domains could require appealing to a third type of explanation that we call sociostructural explanation. The relevance of this explanation type is motivated by the fact that machine learning models are not isolated entities but are embedded within and shaped by social structures. Sociostructural explanations aim to illustrate how social structures contribute to and partially explain the outputs of machine learning models. We demonstrate the importance of sociostructural explanations by examining a racially biased healthcare allocation algorithm. Our proposal highlights the need for transparency beyond model interpretability, understanding the outputs of machine learning systems could require a broader analysis that extends beyond the understanding of the machine learning model itself.