Fast and Accurate Explanations of Distance-Based Classifiers by Uncovering Latent Explanatory Structures

TL;DR

This paper reveals a hidden neural network structure within distance-based classifiers, enabling the application of Explainable AI techniques like LRP for faster and more accurate explanations.

Contribution

It uncovers a neural network analogy in distance-based classifiers, allowing for improved explanation methods and practical interpretability.

Findings

Our explanation approach outperforms several baselines.

The hidden structure enables effective use of LRP.

Practical use cases demonstrate the method's usefulness.

Abstract

Distance-based classifiers, such as k-nearest neighbors and support vector machines, continue to be a workhorse of machine learning, widely used in science and industry. In practice, to derive insights from these models, it is also important to ensure that their predictions are explainable. While the field of Explainable AI has supplied methods that are in principle applicable to any model, it has also emphasized the usefulness of latent structures (e.g. the sequence of layers in a neural network) to produce explanations. In this paper, we contribute by uncovering a hidden neural network structure in distance-based classifiers (consisting of linear detection units combined with nonlinear pooling layers) upon which Explainable AI techniques such as layer-wise relevance propagation (LRP) become applicable. Through quantitative evaluations, we demonstrate the advantage of our novel explanation approach over several baselines. We also show the overall usefulness of explaining distance-based models through two practical use cases.