Computing fast and accurate maps for explaining classification models

Abstract

Image representations of the behavior of trained machine learning classification models can help machine learning engineers examine various aspects of a model such as how it partitions its data space into decision zones separated by decision boundaries; how training samples support the decision in various parts of the data space; and how close training data is to decision boundaries. Yet, for an image of n×n pixels, all current methods that create such images have a computational complexity of O(n2) which precludes their use in interactive visual analytics scenarios. We present a set of techniques for the fast computation of such image-based classifier representations. Compared to earlier work in this area, we accelerate both so-called decision maps, that compute categorical labels, and classifier maps, that compute real-valued quantities, in O((logn)2) time. Practically, our method has a speed-up of about one order of magnitude and yields results very similar to the ground-truth maps; has no free parameters; is model agnostic; and is simple to implement. We demonstrate our method on several combinations of maps, datasets, and classification models.