Explainable Machine Learning with Prior Knowledge: An Overview
It addresses the need for more insightful explanations in complex models, but is incremental as it builds upon prior work in informed machine learning.
This survey tackles the problem of improving explainability in machine learning by integrating prior knowledge, categorizing existing research into three main approaches and extending an existing taxonomy.
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.