Robust and Explainable Detector of Time Series Anomaly via Augmenting Multiclass Pseudo-Anomalies
This work addresses anomaly contamination in time series data for applications like monitoring and fault detection, representing an incremental improvement over prior augmentation-based methods.
The paper tackles the problem of unsupervised anomaly detection in time series by addressing limitations in existing methods that rely on pseudo-anomaly augmentation, such as poor coverage of anomaly types and sensitivity to false anomalies. It proposes RedLamp, which uses diverse augmentations to generate multiclass pseudo-anomalies with soft labels, achieving improved robustness and explainability, as demonstrated in extensive experiments.
Unsupervised anomaly detection in time series has been a pivotal research area for decades. Current mainstream approaches focus on learning normality, on the assumption that all or most of the samples in the training set are normal. However, anomalies in the training set (i.e., anomaly contamination) can be misleading. Recent studies employ data augmentation to generate pseudo-anomalies and learn the boundary separating the training samples from the augmented samples. Although this approach mitigates anomaly contamination if augmented samples mimic unseen real anomalies, it suffers from several limitations. (1) Covering a wide range of time series anomalies is challenging. (2) It disregards augmented samples that resemble normal samples (i.e., false anomalies). (3) It places too much trust in the labels of training and augmented samples. In response, we propose RedLamp, which employs diverse data augmentations to generate multiclass pseudo-anomalies and learns the multiclass boundary. Such multiclass pseudo-anomalies cover a wide variety of time series anomalies. We conduct multiclass classification using soft labels, which prevents the model from being overconfident and ensures its robustness against contaminated/false anomalies. The learned latent space is inherently explainable as it is trained to separate pseudo-anomalies into multiclasses. Extensive experiments demonstrate the effectiveness of RedLamp in anomaly detection and its robustness against anomaly contamination.