Summary of Self-supervised Spatial-temporal Normality Learning For Time Series Anomaly Detection, by Yutong Chen et al.
Self-Supervised Spatial-Temporal Normality Learning for Time Series Anomaly Detection
by Yutong Chen, Hongzuo Xu, Guansong Pang, Hezhe Qiao, Yuan Zhou, Mingsheng Shang
First submitted to arxiv on: 28 Jun 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed Spatial-Temporal Normality learning (STEN) approach for Time Series Anomaly Detection (TSAD) tackles the challenge of capturing both temporal and spatial relationships in time series data. By integrating a sequence Order prediction-based Temporal Normality learning module with a Distance prediction-based Spatial Normality learning module, STEN learns expressive representations that outperform state-of-the-art methods on five TSAD benchmarks. This innovative approach has significant potential for applications in financial markets, industrial production, and healthcare. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary STEN is a new way to detect unusual patterns in time series data. It looks at both how things change over time and where they are in relation to each other. This helps STEN learn what’s normal and identify when something goes wrong. Scientists tested STEN on several datasets and found it worked much better than current methods. |
Keywords
* Artificial intelligence * Anomaly detection * Time series
