Time Series Anomaly Detection Comparison Hub

Reference Surfaces

Top Papers

• Surprised by Attention: Predictable Query Dynamics for Time Series Anomaly Detection(8.0)

  AxonAD is an unsupervised anomaly detection tool for multivariate time series that leverages predictable query dynamics to enhance detection accuracy.

• DQE: A Semantic-Aware Evaluation Metric for Time Series Anomaly Detection(7.0)

  DQE offers a more reliable and interpretable evaluation metric for time series anomaly detection, addressing limitations of existing methods and enabling more objective progress.

• GNNs for Time Series Anomaly Detection: An Open-Source Framework and a Critical Evaluation(5.0)

  An open-source framework for applying Graph Neural Networks to enhance Time Series Anomaly Detection with improved interpretability.