# CGSTA: Cross-Scale Graph Contrast with Stability-Aware Alignment for Multivariate Time-Series Anomaly Detection

arXiv: https://arxiv.org/abs/2602.20468 · HTML: https://mlsanity.com/paper/2602.20468/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 28 references that are in the map.
- First posted on arXiv 24 Feb 2026.

## Builds on (most cited first, 20 of 20)

- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholding](https://mlsanity.com/paper/1802.04431/) (2018)
- [Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy](https://mlsanity.com/paper/2110.02642/) (2021)
- [Graph Neural Network-Based Anomaly Detection in Multivariate Time Series](https://mlsanity.com/paper/2106.06947/) (2021)
- [DCdetector: Dual Attention Contrastive Representation Learning for Time Series Anomaly Detection](https://mlsanity.com/paper/2306.10347/) (2023)
- [TAB: Unified Benchmarking of Time Series Anomaly Detection Methods](https://mlsanity.com/paper/2506.18046/) (2025)
- [Graph Anomaly Detection via Multi-Scale Contrastive Learning Networks with Augmented View](https://mlsanity.com/paper/2212.00535/) (2022)
- [Time Series Contrastive Learning with Information-Aware Augmentations](https://mlsanity.com/paper/2303.11911/) (2023)
- [TimesURL: Self-supervised Contrastive Learning for Universal Time Series Representation Learning](https://mlsanity.com/paper/2312.15709/) (2023)
- [Soft Contrastive Learning for Time Series](https://mlsanity.com/paper/2312.16424/) (2023)
- [Graph-Augmented Normalizing Flows for Anomaly Detection of Multiple Time Series](https://mlsanity.com/paper/2202.07857/) (2022)
- [Calibrated One-class Classification for Unsupervised Time Series Anomaly Detection](https://mlsanity.com/paper/2207.12201/) (2022)
- [Fully-Connected Spatial-Temporal Graph for Multivariate Time-Series Data](https://mlsanity.com/paper/2309.05305/) (2023)
- [Detecting Multivariate Time Series Anomalies with Zero Known Label](https://mlsanity.com/paper/2208.02108/) (2022)
- [Correlation-aware Spatial-Temporal Graph Learning for Multivariate Time-series Anomaly Detection](https://mlsanity.com/paper/2307.08390/) (2023)
- [CARLA: Self-supervised Contrastive Representation Learning for Time Series Anomaly Detection](https://mlsanity.com/paper/2308.09296/) (2023)
- [Label-Free Multivariate Time Series Anomaly Detection](https://mlsanity.com/paper/2312.11549/) (2023)
- [GCAD: Anomaly Detection in Multivariate Time Series from the Perspective of Granger Causality](https://mlsanity.com/paper/2501.13493/) (2025)
- [Rethinking Sensors Modeling: Hierarchical Information Enhanced Traffic Forecasting](https://mlsanity.com/paper/2309.11284/) (2023)
- [Multivariate Time-Series Anomaly Detection based on Enhancing Graph Attention Networks with Topological Analysis](https://mlsanity.com/paper/2408.13082/) (2024)

## Abstract (arXiv)

Multivariate time-series anomaly detection is essential for reliable industrial control, telemetry, and service monitoring. However, the evolving inter-variable dependencies and inevitable noise render it challenging. Existing methods often use single-scale graphs or instance-level contrast. Moreover, learned dynamic graphs can overfit noise without a stable anchor, causing false alarms or misses. To address these challenges, we propose the CGSTA framework with two key innovations. First, Dynamic Layered Graph Construction (DLGC) forms local, regional, and global views of variable relations for each sliding window; rather than contrasting whole windows, Contrastive Discrimination across Scales (CDS) contrasts graph representations within each view and aligns the same window across views to make learning structure-aware. Second, Stability-Aware Alignment (SAA) maintains a per-scale stable reference learned from normal data and guides the current window's fast-changing graphs toward it to suppress noise. We fuse the multi-scale and temporal features and use a conditional density estimator to produce per-time-step anomaly scores. Across four benchmarks, CGSTA delivers optimal performance on PSM and WADI, and is comparable to the baseline methods on SWaT and SMAP.