Explaining the Predictions of Unsupervised Learning Models
Grégoire Montavon, Jacob Kauffmann, Wojciech Samek, Klaus‐Robert Müller
Abstract
Abstract Unsupervised learning is a subfield of machine learning that focuses on learning the structure of data without making use of labels. This implies a different set of learning algorithms than those used for supervised learning, and consequently, also prevents a direct transposition of Explainable AI (XAI) methods from the supervised to the less studied unsupervised setting. In this chapter, we review our recently proposed ‘neuralization-propagation’ (NEON) approach for bringing XAI to workhorses of unsupervised learning such as kernel density estimation and k-means clustering. NEON first converts (without retraining) the unsupervised model into a functionally equivalent neural network so that, in a second step, supervised XAI techniques such as layer-wise relevance propagation (LRP) can be used. The approach is showcased on two application examples: (1) analysis of spending behavior in wholesale customer data and (2) analysis of visual features in industrial and scene images.