# Angel or Devil: Discriminating Hard Samples and Anomaly Contaminations for Unsupervised Time Series Anomaly Detection

arXiv: https://arxiv.org/abs/2410.21322 · HTML: https://mlsanity.com/paper/2410.21322/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 51 references that are in the map.
- First posted on arXiv 26 Oct 2024.

## Builds on (most cited first, 28 of 28)

- [Deep Reinforcement Learning with Double Q-learning](https://mlsanity.com/paper/1509.06461/) (2015)
- [TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis](https://mlsanity.com/paper/2210.02186/) (2022)
- [A Closer Look at Memorization in Deep Networks](https://mlsanity.com/paper/1706.05394/) (2017)
- [Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholding](https://mlsanity.com/paper/1802.04431/) (2018)
- [Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy](https://mlsanity.com/paper/2110.02642/) (2021)
- [Unsupervised Label Noise Modeling and Loss Correction](https://mlsanity.com/paper/1904.11238/) (2019)
- [TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Data](https://mlsanity.com/paper/2201.07284/) (2022)
- [A Deep Neural Network for Unsupervised Anomaly Detection and Diagnosis in Multivariate Time Series Data](https://mlsanity.com/paper/1811.08055/) (2018)
- [Deep Learning for Anomaly Detection: A Review](https://mlsanity.com/paper/2007.02500/) (2020)
- [Active Bias: Training More Accurate Neural Networks by Emphasizing High Variance Samples](https://mlsanity.com/paper/1704.07433/) (2017)
- [Deep Learning for Time Series Anomaly Detection: A Survey](https://mlsanity.com/paper/2211.05244/) (2022)
- [Gradient Harmonized Single-stage Detector](https://mlsanity.com/paper/1811.05181/) (2018)
- [DCdetector: Dual Attention Contrastive Representation Learning for Time Series Anomaly Detection](https://mlsanity.com/paper/2306.10347/) (2023)
- [Neural Transformation Learning for Deep Anomaly Detection Beyond Images](https://mlsanity.com/paper/2103.16440/) (2021)
- [An Evaluation of Anomaly Detection and Diagnosis in Multivariate Time Series](https://mlsanity.com/paper/2109.11428/) (2021)
- [Deep Weakly-supervised Anomaly Detection](https://mlsanity.com/paper/1910.13601/) (2019)
- [Neural Contextual Anomaly Detection for Time Series](https://mlsanity.com/paper/2107.07702/) (2021)
- [Unsupervised Deep Anomaly Detection for Multi-Sensor Time-Series Signals](https://mlsanity.com/paper/2107.12626/) (2021)
- [Calibrated One-class Classification for Unsupervised Time Series Anomaly Detection](https://mlsanity.com/paper/2207.12201/) (2022)
- [Unsupervised Time Series Outlier Detection with Diversity-Driven Convolutional Ensembles -- Extended Version](https://mlsanity.com/paper/2111.11108/) (2021)
- [Time Series Anomaly Detection for Cyber-Physical Systems via Neural System Identification and Bayesian Filtering](https://mlsanity.com/paper/2106.07992/) (2021)
- [Noise-resistant Deep Metric Learning with Ranking-based Instance Selection](https://mlsanity.com/paper/2103.16047/) (2021)
- [Robust and Explainable Autoencoders for Unsupervised Time Series Outlier Detection---Extended Version](https://mlsanity.com/paper/2204.03341/) (2022)
- [Graph-level Anomaly Detection via Hierarchical Memory Networks](https://mlsanity.com/paper/2307.00755/) (2023)
- [RoSAS: Deep Semi-Supervised Anomaly Detection with Contamination-Resilient Continuous Supervision](https://mlsanity.com/paper/2307.13239/) (2023)
- [Estimating the electrical power output of industrial devices with end-to-end time-series classification in the presence of label noise](https://mlsanity.com/paper/2105.00349/) (2021)
- [Empirical Study of Easy and Hard Examples in CNN Training](https://mlsanity.com/paper/1911.10739/) (2019)
- [Differences Between Hard and Noisy-labeled Samples: An Empirical Study](https://mlsanity.com/paper/2307.10718/) (2023)

## Built on by (most cited first, 1 of 1)

- [AvatarShield: Visual Reinforcement Learning for Human-Centric Synthetic Video Detection](https://mlsanity.com/paper/2505.15173/) (2025)

## Abstract (arXiv)

Training in unsupervised time series anomaly detection is constantly plagued by the discrimination between harmful `anomaly contaminations' and beneficial `hard normal samples'. These two samples exhibit analogous loss behavior that conventional loss-based methodologies struggle to differentiate. To tackle this problem, we propose a novel approach that supplements traditional loss behavior with `parameter behavior', enabling a more granular characterization of anomalous patterns. Parameter behavior is formalized by measuring the parametric response to minute perturbations in input samples. Leveraging the complementary nature of parameter and loss behaviors, we further propose a dual Parameter-Loss Data Augmentation method (termed PLDA), implemented within the reinforcement learning paradigm. During the training phase of anomaly detection, PLDA dynamically augments the training data through an iterative process that simultaneously mitigates anomaly contaminations while amplifying informative hard normal samples. PLDA demonstrates remarkable versatility, which can serve as an additional component that seamlessly integrated with existing anomaly detectors to enhance their detection performance. Extensive experiments on ten datasets show that PLDA significantly improves the performance of four distinct detectors by up to 8%, outperforming three state-of-the-art data augmentation methods.