Learning Representations of Event Time Series with Sparse Autoencoders for Anomaly Detection, Similarity Search, and Unsupervised Classification
This provides a flexible and generalizable solution for anomaly detection and other tasks in domains like astrophysics and cybersecurity, though it appears incremental as it builds on existing autoencoder methods.
The authors tackled the challenge of analyzing unstructured and irregular event time series by proposing novel tensor representations and sparse autoencoders to learn meaningful latent embeddings, demonstrating on an X-ray astronomy dataset that these representations capture temporal and spectral signatures and isolate diverse classes of X-ray transients.
Event time series are sequences of discrete events occurring at irregular time intervals, each associated with a domain-specific observational modality. They are common in domains such as high-energy astrophysics, computational social science, cybersecurity, finance, healthcare, neuroscience, and seismology. Their unstructured and irregular structure poses significant challenges for extracting meaningful patterns and identifying salient phenomena using conventional techniques. We propose novel two- and three-dimensional tensor representations for event time series, coupled with sparse autoencoders that learn physically meaningful latent representations. These embeddings support a variety of downstream tasks, including anomaly detection, similarity-based retrieval, semantic clustering, and unsupervised classification. We demonstrate our approach on a real-world dataset from X-ray astronomy, showing that these representations successfully capture temporal and spectral signatures and isolate diverse classes of X-ray transients. Our framework offers a flexible, scalable, and generalizable solution for analyzing complex, irregular event time series across scientific and industrial domains.