A Survey on Explainable Anomaly Detection
Обзор методов объяснимого обнаружения аномалий
2023-07-15
SCID: 54.1/7hgugxef
Discuss with AI
anomaly detectionexplainabilityexplainable anomaly detectionsafety-critical domainstaxonomy
Figures from the paper
Abstract (AI)
In the past two decades, most research on anomaly detection has focused on improving the accuracy of the detection, while largely ignoring the explainability of the corresponding methods and thus leaving the explanation of outcomes to practitioners. As anomaly detection algorithms are increasingly used in safety-critical domains, providing explanations for the high-stakes decisions made in those domains has become an ethical and regulatory requirement. Therefore, this work provides a comprehensive and structured survey on state-of-the-art explainable anomaly detection techniques. We propose a taxonomy based on the main aspects that characterise each explainable anomaly detection technique, aiming to help practitioners and researchers find the explainable anomaly detection method that best suits their needs.
Key Findings
1
Anomaly detection research has predominantly prioritized detection accuracy while largely neglecting explainability of algorithmic outcomes.
2
Explainability is increasingly necessary because anomaly detection supports high-stakes decisions in safety-critical domains subject to ethical and regulatory requirements.
3
It introduces a taxonomy organized around the main characteristics of explainable anomaly detection methods to support method selection by practitioners and researchers.
4
The paper presents a comprehensive, structured survey of state-of-the-art explainable anomaly detection techniques.
Research Object
Explainable anomaly detection techniques
Research Subject
the explainability of anomaly detection outcomes and techniques, including their characterization and suitability for high-stakes decisions
Publication Details
Publication Date
2023-07-15
Journal
ACM Transactions on Knowledge Discovery from Data
Publisher
Association for Computing Machinery
ISSN
1556-4681
Cited by
294
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai14
XGBoost2016
A Unified Approach to Interpreting Model Predictions2017
"Why Should I Trust You?": Explaining the Predictions of Any Classifier2016
Regularization and Variable Selection Via the Elastic Net2005
Anomaly detection: A survey2009
Towards A Rigorous Science of Interpretable Machine Learning2017
Isolation Forest2008
Deep Learning for Anomaly Detection: A Review2021
Machine Learning Interpretability: A Survey on Methods and Metrics2019
A Unifying Review of Deep and Shallow Anomaly Detection2021
A Survey on the Explainability of Supervised Machine Learning2021
Multivariate Time Series Anomaly Detection and Interpretation using Hierarchical Inter-Metric and Temporal Embedding2021
A Survey of Methods for Explaining Black Box Models2018
Evaluating the Quality of Machine Learning Explanations: A Survey on Methods and Metrics2021