# Robust and Explainable Autoencoders for Unsupervised Time Series Outlier Detection---Extended Version

arXiv: https://arxiv.org/abs/2204.03341 · HTML: https://mlsanity.com/paper/2204.03341/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 65 references that are in the map.
- First posted on arXiv 7 Apr 2022.

## Builds on (most cited first, 18 of 18)

- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [Techniques for Interpretable Machine Learning](https://mlsanity.com/paper/1808.00033/) (2018)
- [Unsupervised Anomaly Detection via Variational Auto-Encoder for Seasonal KPIs in Web Applications](https://mlsanity.com/paper/1802.03903/) (2018)
- [LSTM-based Encoder-Decoder for Multi-sensor Anomaly Detection](https://mlsanity.com/paper/1607.00148/) (2016)
- [On Deep Multi-View Representation Learning: Objectives and Optimization](https://mlsanity.com/paper/1602.01024/) (2016)
- [Interpretable Convolutional Neural Networks](https://mlsanity.com/paper/1710.00935/) (2017)
- [Rethinking the Hyperparameters for Fine-tuning](https://mlsanity.com/paper/2002.11770/) (2020)
- [Convergence Analysis of Alternating Direction Method of Multipliers for a Family of Nonconvex Problems](https://mlsanity.com/paper/1410.1390/) (2014)
- [Towards Spatio-Temporal Aware Traffic Time Series Forecasting--Full Version](https://mlsanity.com/paper/2203.15737/) (2022)
- [AutoCTS: Automated Correlated Time Series Forecasting -- Extended Version](https://mlsanity.com/paper/2112.11174/) (2021)
- [Unsupervised Path Representation Learning with Curriculum Negative Sampling](https://mlsanity.com/paper/2106.09373/) (2021)
- [Tensor Robust Principal Component Analysis: Exact Recovery of Corrupted Low-Rank Tensors via Convex Optimization](https://mlsanity.com/paper/1708.04181/) (2017)
- [Unsupervised Time Series Outlier Detection with Diversity-Driven Convolutional Ensembles -- Extended Version](https://mlsanity.com/paper/2111.11108/) (2021)
- [Graph Attention Recurrent Neural Networks for Correlated Time Series Forecasting -- Full version](https://mlsanity.com/paper/2103.10760/) (2021)
- [A General Analysis of the Convergence of ADMM](https://mlsanity.com/paper/1502.02009/) (2015)
- [Matrix Profile Goes MAD: Variable-Length Motif And Discord Discovery in Data Series](https://mlsanity.com/paper/2008.13447/) (2020)
- [Exactly Robust Kernel Principal Component Analysis](https://mlsanity.com/paper/1802.10558/) (2018)

## Built on by (most cited first, 19 of 19)

- [TFB: Towards Comprehensive and Fair Benchmarking of Time Series Forecasting Methods](https://mlsanity.com/paper/2403.20150/) (2024)
- [LightTS: Lightweight Time Series Classification with Adaptive Ensemble Distillation -- Extended Version](https://mlsanity.com/paper/2302.12721/) (2023)
- [Calibrated One-class Classification for Unsupervised Time Series Anomaly Detection](https://mlsanity.com/paper/2207.12201/) (2022)
- [Joint Neural Architecture and Hyperparameter Search for Correlated Time Series Forecasting](https://mlsanity.com/paper/2211.16126/) (2022)
- [Fully Automated Correlated Time Series Forecasting in Minutes](https://mlsanity.com/paper/2411.05833/) (2024)
- [Learning Informative Representation for Fairness-aware Multivariate Time-series Forecasting: A Group-based Perspective](https://mlsanity.com/paper/2301.11535/) (2023)
- [QCore: Data-Efficient, On-Device Continual Calibration for Quantized Models -- Extended Version](https://mlsanity.com/paper/2404.13990/) (2024)
- [Orca: Ocean Significant Wave Height Estimation with Spatio-temporally Aware Large Language Models](https://mlsanity.com/paper/2407.20053/) (2024)
- [An Encode-then-Decompose Approach to Unsupervised Time Series Anomaly Detection on Contaminated Training Data--Extended Version](https://mlsanity.com/paper/2510.18998/) (2025)
- [Data Driven Decision Making with Time Series and Spatio-temporal Data](https://mlsanity.com/paper/2503.08473/) (2025)
- [FoMo X: Modular Explainability Signals for Outlier Detection Foundation Models](https://mlsanity.com/paper/2603.17570/) (2026)
- [Multi-Normal Prototypes Learning for Weakly Supervised Anomaly Detection](https://mlsanity.com/paper/2408.14498/) (2024)
- [Interpreting Outliers in Time Series Data through Decoding Autoencoder](https://mlsanity.com/paper/2409.01713/) (2024)
- [Angel or Devil: Discriminating Hard Samples and Anomaly Contaminations for Unsupervised Time Series Anomaly Detection](https://mlsanity.com/paper/2410.21322/) (2024)
- [COGNOS: Universal Enhancement for Time Series Anomaly Detection via Constrained Gaussian-Noise Optimization and Smoothing](https://mlsanity.com/paper/2511.06894/) (2025)
- [Algorithmic Recourse in Abnormal Multivariate Time Series](https://mlsanity.com/paper/2309.16896/) (2023)
- [AutoFed: Personalized Federated Traffic Prediction via Adaptive Prompt](https://mlsanity.com/paper/2512.24625/) (2025)
- [PeakFocus: Bridging Peak Localization and Intensity Regression via a Unified Multi-Scale Framework for Electricity Load Forecasting](https://mlsanity.com/paper/2605.21550/) (2026)
- [Towards Robust Time Series Learning via Capacity-Centric Modulation](https://mlsanity.com/paper/2609.39489/) (2026)

## Abstract (arXiv)

Time series data occurs widely, and outlier detection is a fundamental problem in data mining, which has numerous applications. Existing autoencoder-based approaches deliver state-of-the-art performance on challenging real-world data but are vulnerable to outliers and exhibit low explainability. To address these two limitations, we propose robust and explainable unsupervised autoencoder frameworks that decompose an input time series into a clean time series and an outlier time series using autoencoders. Improved explainability is achieved because clean time series are better explained with easy-to-understand patterns such as trends and periodicities. We provide insight into this by means of a post-hoc explainability analysis and empirical studies. In addition, since outliers are separated from clean time series iteratively, our approach offers improved robustness to outliers, which in turn improves accuracy. We evaluate our approach on five real-world datasets and report improvements over the state-of-the-art approaches in terms of robustness and explainability. This is an extended version of "Robust and Explainable Autoencoders for Unsupervised Time Series Outlier Detection", to appear in IEEE ICDE 2022.