Explainable Machine Learning with Prior Knowledge: An Overview
arXiv:2105.10172
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.
References in corpus (9)
- Understanding Neural Networks Through Deep Visualization
- Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Models
- A Survey on the Explainability of Supervised Machine Learning
- What Does Explainable AI Really Mean? A New Conceptualization of Perspectives
- Distilling a Neural Network Into a Soft Decision Tree
- Interactively Transferring CNN Patterns for Part Localization
- Incorporating Biological Knowledge with Factor Graph Neural Network for Interpretable Deep Learning
- From Shallow to Deep Interactions Between Knowledge Representation, Reasoning and Machine Learning (Kay R. Amel group)
- Teaching the Machine to Explain Itself using Domain Knowledge