RESTAD: REconstruction and Similarity based Transformer for time series Anomaly Detection
This work addresses anomaly detection in time series for domains with scarce labeled data, offering an incremental improvement over existing unsupervised methods.
The paper tackled the problem of detecting subtle anomalies in time series data with limited labeled data by introducing RESTAD, a Transformer-based model that combines reconstruction errors with similarity scores from an RBF layer, and it outperformed established baselines on multiple benchmarks.
Anomaly detection in time series data is crucial across various domains. The scarcity of labeled data for such tasks has increased the attention towards unsupervised learning methods. These approaches, often relying solely on reconstruction error, typically fail to detect subtle anomalies in complex datasets. To address this, we introduce RESTAD, an adaptation of the Transformer model by incorporating a layer of Radial Basis Function (RBF) neurons within its architecture. This layer fits a non-parametric density in the latent representation, such that a high RBF output indicates similarity with predominantly normal training data. RESTAD integrates the RBF similarity scores with the reconstruction errors to increase sensitivity to anomalies. Our empirical evaluations demonstrate that RESTAD outperforms various established baselines across multiple benchmark datasets.