mlsanityData to 7 Oct 2026

Towards Explaining Anomalies: A Deep Taylor Decomposition of One-Class Models

arXiv 1805.06230 ↗First posted 16 May 2018stat.ML cs.LGcited by 24

Not on the map. Why?

Abstract (arXiv)

A common machine learning task is to discriminate between normal and anomalous data points. In practice, it is not always sufficient to reach high accuracy at this task, one also would like to understand why a given data point has been predicted in a certain way. We present a new principled approach for one-class SVMs that decomposes outlier predictions in terms of input variables. The method first recomposes the one-class model as a neural network with distance functions and min-pooling, and then performs a deep Taylor decomposition (DTD) of the model output. The proposed One-Class DTD is applicable to a number of common distance-based SVM kernels and is able to reliably explain a wide set of data anomalies. Furthermore, it outperforms baselines such as sensitivity analysis, nearest neighbor, or simple edge detection.

Key facts. Cited by 24 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 May 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 7; 2022: 9; 2023: 2; 2024: 3; 2025: 1; 2026: 2.

24 papers.

Sort:

  1. 2021This looks more like that: Enhancing Self-Explaining Models by Prototypical Relevance Propagationcited by 43
  2. 2022A Survey on Explainable Anomaly Detectioncited by 39
  3. 2021Toward Explainable AI for Regression Modelscited by 30
  4. 2022Explainable Intrusion Detection Systems (X-IDS): A Survey of Current Methods, Challenges, and Opportunitiescited by 25
  5. 2024The Clever Hans Effect in Unsupervised Learningcited by 24
  6. 2021DeepAID: Interpreting and Improving Deep Learning-based Anomaly Detection in Security Applicationscited by 18
  7. 2022Data-Efficient and Interpretable Tabular Anomaly Detectioncited by 15
  8. 2021DI-AA: An Interpretable White-box Attack for Fooling Deep Neural Networkscited by 10
  9. 2024AI-based Anomaly Detection for Clinical-Grade Histopathological Diagnosticscited by 8
  10. 2022A general-purpose method for applying Explainable AI for Anomaly Detectioncited by 7
  11. 2022On Root Cause Localization and Anomaly Mitigation through Causal Inferencecited by 6
  12. 2022Trustworthy Anomaly Detection: A Surveycited by 5
12 more
  1. 2022Framing Algorithmic Recourse for Anomaly Detectioncited by 5
  2. 2022Explaining Anomalies using Denoising Autoencoders for Financial Tabular Datacited by 4
  3. 2022Self-Supervised Training with Autoencoders for Visual Anomaly Detectioncited by 3
  4. 2023Insightful analysis of historical sources at scales beyond human capabilities using unsupervised Machine Learning and XAIcited by 3
  5. 2026Interpretable Maximum Margin Deep Anomaly Detectioncited by 2
  6. 2021Towards Interpretable Ensemble Learning for Image-based Malware Detectioncited by 1
  7. 2021Towards interpreting ML-based automated malware detection models: a surveycited by 1
  8. 2021Detection of Dataset Shifts in Learning-Enabled Cyber-Physical Systems using Variational Autoencoder for Regressioncited by 0
  9. 2023A Novel Dual-pooling Attention Module for UAV Vehicle Re-identificationcited by 0
  10. 2024A Safe Screening Rule with Bi-level Optimization of nu Support Vector Machinecited by 0
  11. 2025Fast and Accurate Explanations of Distance-Based Classifiers by Uncovering Latent Explanatory Structurescited by 0
  12. 2026Hidden Monotonicity: Explaining Deep Neural Networks via their DC Decompositioncited by 0