Towards explaining anomalies: A deep Taylor decomposition of one-class models

Jacob Kauffmann, Klaus Robert Müller, Grégoire Montavon

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Detecting anomalies in the data is a common machine learning task, with numerous applications in the sciences and industry. In practice, it is not always sufficient to reach high detection accuracy, one would also like to be able to understand why a given data point has been predicted to be anomalous. We propose a principled approach for one-class SVMs (OC-SVM), that draws on the novel insight that these models can be rewritten as distance/pooling neural networks. This ‘neuralization’ step lets us apply deep Taylor decomposition (DTD), a methodology that leverages the model structure in order to quickly and reliably explain decisions in terms of input features. The proposed method (called ‘OC-DTD’) is applicable to a number of common distance-based kernel functions, and it outperforms baselines such as sensitivity analysis, distance to nearest neighbor, or edge detection.

Original languageEnglish
Article number107198
JournalPattern Recognition
Volume101
DOIs
Publication statusPublished - 2020 May

Keywords

  • Deep Taylor decomposition
  • Explainable machine learning
  • Kernel machines
  • Outlier detection
  • Unsupervised learning

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Fingerprint Dive into the research topics of 'Towards explaining anomalies: A deep Taylor decomposition of one-class models'. Together they form a unique fingerprint.

  • Cite this