# AcME-AD: Accelerated Model Explanations for Anomaly Detection

arXiv: https://arxiv.org/abs/2403.01245 · HTML: https://mlsanity.com/paper/2403.01245/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 35 references that are in the map.
- First posted on arXiv 2 Mar 2024.

## Builds on (most cited first, 14 of 14)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [ADBench: Anomaly Detection Benchmark](https://mlsanity.com/paper/2206.09426/) (2022)
- [ECOD: Unsupervised Outlier Detection Using Empirical Cumulative Distribution Functions](https://mlsanity.com/paper/2201.00382/) (2022)
- [Explainable AI (XAI): A Systematic Meta-Survey of Current Challenges and Future Opportunities](https://mlsanity.com/paper/2111.06420/) (2021)
- [Extended Isolation Forest](https://mlsanity.com/paper/1811.02141/) (2018)
- [A Survey on Explainable Anomaly Detection](https://mlsanity.com/paper/2210.06959/) (2022)
- [XAI Beyond Classification: Interpretable Neural Clustering](https://mlsanity.com/paper/1808.07292/) (2018)
- [An Explainable Artificial Intelligence Approach for Unsupervised Fault Detection and Diagnosis in Rotating Machinery](https://mlsanity.com/paper/2102.11848/) (2021)
- [Shapley Values of Reconstruction Errors of PCA for Explaining Anomaly Detection](https://mlsanity.com/paper/1909.03495/) (2019)
- [Interpretable Anomaly Detection with DIFFI: Depth-based Isolation Forest Feature Importance](https://mlsanity.com/paper/2007.11117/) (2020)
- [AcME -- Accelerated Model-agnostic Explanations: Fast Whitening of the Machine-Learning Black Box](https://mlsanity.com/paper/2112.12635/) (2021)
- [Rule Extraction in Unsupervised Anomaly Detection for Model Explainability: Application to OneClass SVM](https://mlsanity.com/paper/1911.09315/) (2019)
- [Why Are You Weird? Infusing Interpretability in Isolation Forest for Anomaly Detection](https://mlsanity.com/paper/2112.06858/) (2021)
- [Enhancing Interpretability and Generalizability in Extended Isolation Forests](https://mlsanity.com/paper/2310.05468/) (2023)

## Built on by (most cited first, 2 of 2)

- [Enabling Efficient and Flexible Interpretability of Data-driven Anomaly Detection in Industrial Processes with AcME-AD](https://mlsanity.com/paper/2404.18525/) (2024)
- [Towards Transparent and Efficient Anomaly Detection in Industrial Processes through ExIFFI](https://mlsanity.com/paper/2405.01158/) (2024)

## Abstract (arXiv)

Pursuing fast and robust interpretability in Anomaly Detection is crucial, especially due to its significance in practical applications. Traditional Anomaly Detection methods excel in outlier identification but are often black-boxes, providing scant insights into their decision-making process. This lack of transparency compromises their reliability and hampers their adoption in scenarios where comprehending the reasons behind anomaly detection is vital. At the same time, getting explanations quickly is paramount in practical scenarios. To bridge this gap, we present AcME-AD, a novel approach rooted in Explainable Artificial Intelligence principles, designed to clarify Anomaly Detection models for tabular data. AcME-AD transcends the constraints of model-specific or resource-heavy explainability techniques by delivering a model-agnostic, efficient solution for interoperability. It offers local feature importance scores and a what-if analysis tool, shedding light on the factors contributing to each anomaly, thus aiding root cause analysis and decision-making. This paper elucidates AcME-AD's foundation, its benefits over existing methods, and validates its effectiveness with tests on both synthetic and real datasets. AcME-AD's implementation and experiment replication code is accessible in a public repository.