Explainable Machine Learning with Prior Knowledge: An Overview

TL;DR

This survey reviews how incorporating prior knowledge into machine learning enhances explainability, categorizing current research and highlighting future challenges in making models more interpretable.

Contribution

It provides a comprehensive categorization of methods integrating prior knowledge into explainability, extending existing taxonomies and outlining open research challenges.

Findings

Categorizes current research into three main approaches.

Highlights the importance of prior knowledge for explainability.

Identifies open challenges and future research directions.

Abstract

This survey presents an overview of integrating prior knowledge into machine learning systems in order to improve explainability. The complexity of machine learning models has elicited research to make them more explainable. However, most explainability methods cannot provide insight beyond the given data, requiring additional information about the context. We propose to harness prior knowledge to improve upon the explanation capabilities of machine learning models. In this paper, we present a categorization of current research into three main categories which either integrate knowledge into the machine learning pipeline, into the explainability method or derive knowledge from explanations. To classify the papers, we build upon the existing taxonomy of informed machine learning and extend it from the perspective of explainability. We conclude with open challenges and research directions.