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

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.

References in corpus (10)

• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications
• Explaining NonLinear Classification Decisions with Deep Taylor Decomposition
• Machine Learning of Accurate Energy-Conserving Molecular Force Fields
• Deep Neural Networks and Tabular Data: A Survey
• Higher-Order Explanations of Graph Neural Networks via Relevant Walks
• From Clustering to Cluster Explanations via Neural Networks
• Towards Explaining Anomalies: A Deep Taylor Decomposition of One-Class Models
• The Clever Hans Effect in Unsupervised Learning
• Explaining Predictive Uncertainty by Exposing Second-Order Effects