mlsanityData to 7 Oct 2026

A Revealing Large-Scale Evaluation of Unsupervised Anomaly Detection Algorithms

arXiv 2204.09825 ↗First posted 21 Apr 2022cs.LG cs.AI cs.CRcited by 10

Not on the map. Why?

Abstract (arXiv)

Anomaly detection has many applications ranging from bank-fraud detection and cyber-threat detection to equipment maintenance and health monitoring. However, choosing a suitable algorithm for a given application remains a challenging design decision, often informed by the literature on anomaly detection algorithms. We extensively reviewed twelve of the most popular unsupervised anomaly detection methods. We observed that, so far, they have been compared using inconsistent protocols - the choice of the class of interest or the positive class, the split of training and test data, and the choice of hyperparameters - leading to ambiguous evaluations. This observation led us to define a coherent evaluation protocol which we then used to produce an updated and more precise picture of the relative performance of the twelve methods on five widely used tabular datasets. While our evaluation cannot pinpoint a method that outperforms all the others on all datasets, it identifies those that stand out and revise misconceived knowledge about their relative performances.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 16 of its 41 references that are in the map. First posted on arXiv 21 Apr 2022.

Builds on

16 of 41 references.

References · 16

  1. 2021Deep Reinforcement Learning at the Edge of the Statistical Precipicecited by 781
  2. 2019Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detectioncited by 560
  3. 2020A Unifying Review of Deep and Shallow Anomaly Detectioncited by 423
  4. 2019Deep Learning for Anomaly Detection: A Surveycited by 357
  5. 2020Improving Reproducibility in Machine Learning Research (A Report from the NeurIPS 2019 Reproducibility Program)cited by 318
  6. 2020A Metric Learning Reality Checkcited by 317
  7. 2020Classification-Based Anomaly Detection for General Datacited by 210
  8. 2021Accounting for Variance in Machine Learning Benchmarkscited by 195
  9. 2020DROCC: Deep Robust One-Class Classificationcited by 121
  10. 2018Adversarially Learned Anomaly Detectioncited by 115
  11. 2016Deep Structured Energy Based Models for Anomaly Detectioncited by 113
  12. 2021Neural Transformation Learning for Deep Anomaly Detection Beyond Imagescited by 98
4 more
  1. 2019A Step Toward Quantifying Independently Reproducible Machine Learning Researchcited by 77
  2. 2021Scientific Credibility of Machine Translation Research: A Meta-Evaluation of 769 Paperscited by 70
  3. 2017Knowledge Base Completion: Baselines Strike Backcited by 39
  4. 2021Anomaly Detection: How to Artificially Increase your F1-Score with a Biased Evaluation Protocolcited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 2; 2024: 4; 2025: 1; 2026: 1.

10 papers.

  1. 2024A Closer Look at AUROC and AUPRC under Class Imbalancecited by 56
  2. 2023Deep Anomaly Detection under Labeling Budget Constraintscited by 9
  3. 2022Unsupervised Anomaly Detection for Auditing Data and Impact of Categorical Encodingscited by 3
  4. 2024Deep Learning for Network Anomaly Detection under Data Contamination: Evaluating Robustness and Mitigating Performance Degradationcited by 3
  5. 2024FedAD-Bench: A Unified Benchmark for Federated Unsupervised Anomaly Detection in Tabular Datacited by 3
  6. 2022Robustness Evaluation of Deep Unsupervised Learning Algorithms for Intrusion Detection Systemscited by 2
  7. 2023Zero-Shot Anomaly Detection via Batch Normalizationcited by 1
  8. 2024Generalizability of experimental studiescited by 0
  9. 2025An Investigation into the Performance of Non-Contrastive Self-Supervised Learning Methods for Network Intrusion Detectioncited by 0
  10. 2026Attention, Anomalies! Handling Attention Layers in Unsupervised Federated Outlier Detectioncited by 0