Towards Analogy-Based Explanations in Machine Learning

TL;DR

This paper advocates for analogy-based explanations in machine learning, emphasizing their potential to enhance interpretability and complement existing similarity-based methods, supported by illustrative examples.

Contribution

It introduces the concept of analogy-based explanations as a novel approach to improve interpretability in machine learning models.

Findings

Analogy-based explanations can complement similarity-based explanations.

Analogical reasoning is useful for interpretability and explainability.

Examples demonstrate the potential usefulness of analogy-based explanations.

Abstract

Principles of analogical reasoning have recently been applied in the context of machine learning, for example to develop new methods for classification and preference learning. In this paper, we argue that, while analogical reasoning is certainly useful for constructing new learning algorithms with high predictive accuracy, is is arguably not less interesting from an interpretability and explainability point of view. More specifically, we take the view that an analogy-based approach is a viable alternative to existing approaches in the realm of explainable AI and interpretable machine learning, and that analogy-based explanations of the predictions produced by a machine learning algorithm can complement similarity-based explanations in a meaningful way. To corroborate these claims, we outline the basic idea of an analogy-based explanation and illustrate its potential usefulness by means of some examples.