# Diverse Counterfactual Explanations for Anomaly Detection in Time Series

arXiv: https://arxiv.org/abs/2203.11103 · HTML: https://mlsanity.com/paper/2203.11103/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 40 references that are in the map.
- First posted on arXiv 21 Mar 2022.

## Builds on (most cited first, 24 of 24)

- [An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling](https://mlsanity.com/paper/1803.01271/) (2018)
- [Explanation in Artificial Intelligence: Insights from the Social Sciences](https://mlsanity.com/paper/1706.07269/) (2017)
- [Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR](https://mlsanity.com/paper/1711.00399/) (2017)
- [Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations](https://mlsanity.com/paper/1905.07697/) (2019)
- [Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholding](https://mlsanity.com/paper/1802.04431/) (2018)
- [RETAIN: An Interpretable Predictive Model for Healthcare using Reverse Time Attention Mechanism](https://mlsanity.com/paper/1608.05745/) (2016)
- [Understanding Deep Networks via Extremal Perturbations and Smooth Masks](https://mlsanity.com/paper/1910.08485/) (2019)
- [Explainable Machine Learning in Deployment](https://mlsanity.com/paper/1909.06342/) (2019)
- [The What-If Tool: Interactive Probing of Machine Learning Models](https://mlsanity.com/paper/1907.04135/) (2019)
- [Model-Agnostic Counterfactual Explanations for Consequential Decisions](https://mlsanity.com/paper/1905.11190/) (2019)
- [A review on outlier/anomaly detection in time series data](https://mlsanity.com/paper/2002.04236/) (2020)
- [Multi-Objective Counterfactual Explanations](https://mlsanity.com/paper/2004.11165/) (2020)
- [High-Dimensional Multivariate Forecasting with Low-Rank Gaussian Copula Processes](https://mlsanity.com/paper/1910.03002/) (2019)
- [Efficient Search for Diverse Coherent Explanations](https://mlsanity.com/paper/1901.04909/) (2019)
- [TimeSHAP: Explaining Recurrent Models through Sequence Perturbations](https://mlsanity.com/paper/2012.00073/) (2020)
- [Explaining Time Series Predictions with Dynamic Masks](https://mlsanity.com/paper/2106.05303/) (2021)
- [Instance-based Counterfactual Explanations for Time Series Classification](https://mlsanity.com/paper/2009.13211/) (2020)
- [Beyond Trivial Counterfactual Explanations with Diverse Valuable Explanations](https://mlsanity.com/paper/2103.10226/) (2021)
- [Counterfactual Explanations for Machine Learning on Multivariate Time Series Data](https://mlsanity.com/paper/2008.10781/) (2020)
- [Neural Contextual Anomaly Detection for Time Series](https://mlsanity.com/paper/2107.07702/) (2021)
- [An Exact and Robust Conformal Inference Method for Counterfactual and Synthetic Controls](https://mlsanity.com/paper/1712.09089/) (2017)
- [Recurrent Neural Network Attention Mechanisms for Interpretable System Log Anomaly Detection](https://mlsanity.com/paper/1803.04967/) (2018)
- [Diverse, Global and Amortised Counterfactual Explanations for Uncertainty Estimates](https://mlsanity.com/paper/2112.02646/) (2021)
- [Series Saliency: Temporal Interpretation for Multivariate Time Series Forecasting](https://mlsanity.com/paper/2012.09324/) (2020)

## Built on by (most cited first, 10 of 10)

- [Explainable Time Series Anomaly Detection using Masked Latent Generative Modeling](https://mlsanity.com/paper/2311.12550/) (2023)
- [Reimagining Anomalies: What If Anomalies Were Normal?](https://mlsanity.com/paper/2402.14469/) (2024)
- [Counterfactual-based Root Cause Analysis for Dynamical Systems](https://mlsanity.com/paper/2406.08106/) (2024)
- [AR-Pro: Counterfactual Explanations for Anomaly Repair with Formal Properties](https://mlsanity.com/paper/2410.24178/) (2024)
- [Towards Meaningful Anomaly Detection: The Effect of Counterfactual Explanations on the Investigation of Anomalies in Multivariate Time Series](https://mlsanity.com/paper/2302.03302/) (2023)
- [Personalized Path Recourse for Reinforcement Learning Agents](https://mlsanity.com/paper/2312.08724/) (2023)
- [No Dtrain: Model-Agnostic Counterfactual Explanations Using Reinforcement Learning](https://mlsanity.com/paper/2405.18563/) (2024)
- [Counterfactual Explanation for Auto-Encoder Based Time-Series Anomaly Detection](https://mlsanity.com/paper/2501.02069/) (2025)
- [Counterfactual Explanation for Multivariate Time Series Forecasting with Exogenous Variables](https://mlsanity.com/paper/2511.06906/) (2025)
- [ConceptCF: Concept-based Counterfactuals for the Explainability of Time Series](https://mlsanity.com/paper/2607.18748/) (2026)

## Abstract (arXiv)

Data-driven methods that detect anomalies in times series data are ubiquitous in practice, but they are in general unable to provide helpful explanations for the predictions they make. In this work we propose a model-agnostic algorithm that generates counterfactual ensemble explanations for time series anomaly detection models. Our method generates a set of diverse counterfactual examples, i.e, multiple perturbed versions of the original time series that are not considered anomalous by the detection model. Since the magnitude of the perturbations is limited, these counterfactuals represent an ensemble of inputs similar to the original time series that the model would deem normal. Our algorithm is applicable to any differentiable anomaly detection model. We investigate the value of our method on univariate and multivariate real-world datasets and two deep-learning-based anomaly detection models, under several explainability criteria previously proposed in other data domains such as Validity, Plausibility, Closeness and Diversity. We show that our algorithm can produce ensembles of counterfactual examples that satisfy these criteria and thanks to a novel type of visualisation, can convey a richer interpretation of a model's internal mechanism than existing methods. Moreover, we design a sparse variant of our method to improve the interpretability of counterfactual explanations for high-dimensional time series anomalies. In this setting, our explanation is localised on only a few dimensions and can therefore be communicated more efficiently to the model's user.