{"ID":2868253,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.17235","arxiv_id":"2509.17235","title":"Prospective Multi-Graph Cohesion for Multivariate Time Series Anomaly Detection","abstract":"Anomaly detection in high-dimensional time series data is pivotal for numerous industrial applications. Recent advances in multivariate time series anomaly detection (TSAD) have increasingly leveraged graph structures to model inter-variable relationships, typically employing Graph Neural Networks (GNNs). Despite their promising results, existing methods often rely on a single graph representation, which are insufficient for capturing the complex, diverse relationships inherent in multivariate time series. To address this, we propose the Prospective Multi-Graph Cohesion (PMGC) framework for multivariate TSAD. PMGC exploits spatial correlations by integrating a long-term static graph with a series of short-term instance-wise dynamic graphs, regulated through a graph cohesion loss function. Our theoretical analysis shows that this loss function promotes diversity among dynamic graphs while aligning them with the stable long-term relationships encapsulated by the static graph. Additionally, we introduce a \"prospective graphing\" strategy to mitigate the limitations of traditional forecasting-based TSAD methods, which often struggle with unpredictable future variations. This strategy allows the model to accurately reflect concurrent inter-series relationships under normal conditions, thereby enhancing anomaly detection efficacy. Empirical evaluations on real-world datasets demonstrate the superior performance of our method compared to existing TSAD techniques.","short_abstract":"Anomaly detection in high-dimensional time series data is pivotal for numerous industrial applications. Recent advances in multivariate time series anomaly detection (TSAD) have increasingly leveraged graph structures to model inter-variable relationships, typically employing Graph Neural Networks (GNNs). Despite their...","url_abs":"https://arxiv.org/abs/2509.17235","url_pdf":"https://arxiv.org/pdf/2509.17235v1","authors":"[\"Jiazhen Chen\",\"Mingbin Feng\",\"Tony S. Wirjanto\"]","published":"2025-09-21T21:00:21Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[\"Graph Neural Network\"]","has_code":false}