Lossy Compression for Robust Unsupervised Time-Series Anomaly Detection
This addresses the limitation in many state-of-the-art unsupervised methods that require training only on normal data, offering a more realistic and robust approach for anomaly detection in time-series applications.
The paper tackles the problem of unsupervised time-series anomaly detection by proposing a lossy compression-based autoencoder that uses a rate-distortion loss and entropy bottleneck to learn a robust latent representation, achieving high accuracy in detecting anomalies even when trained with some unlabelled anomalous data.
A new Lossy Causal Temporal Convolutional Neural Network Autoencoder for anomaly detection is proposed in this work. Our framework uses a rate-distortion loss and an entropy bottleneck to learn a compressed latent representation for the task. The main idea of using a rate-distortion loss is to introduce representation flexibility that ignores or becomes robust to unlikely events with distinctive patterns, such as anomalies. These anomalies manifest as unique distortion features that can be accurately detected in testing conditions. This new architecture allows us to train a fully unsupervised model that has high accuracy in detecting anomalies from a distortion score despite being trained with some portion of unlabelled anomalous data. This setting is in stark contrast to many of the state-of-the-art unsupervised methodologies that require the model to be only trained on "normal data". We argue that this partially violates the concept of unsupervised training for anomaly detection as the model uses an informed decision that selects what is normal from abnormal for training. Additionally, there is evidence to suggest it also effects the models ability at generalisation. We demonstrate that models that succeed in the paradigm where they are only trained on normal data fail to be robust when anomalous data is injected into the training. In contrast, our compression-based approach converges to a robust representation that tolerates some anomalous distortion. The robust representation achieved by a model using a rate-distortion loss can be used in a more realistic unsupervised anomaly detection scheme.