Towards Analogy-Based Explanations in Machine Learning
This work addresses the need for more interpretable explanations in machine learning, though it appears incremental as it builds on existing analogical reasoning concepts without introducing a new paradigm.
The paper argues that analogy-based reasoning can serve as a viable alternative to existing methods in explainable AI, complementing similarity-based explanations to enhance interpretability of machine learning predictions, and illustrates this with examples.
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.