Summary of Scalable Temporal Anomaly Causality Discovery in Large Systems: Achieving Computational Efficiency with Binary Anomaly Flag Data, by Mulugeta Weldezgina Asres et al.
Scalable Temporal Anomaly Causality Discovery in Large Systems: Achieving Computational Efficiency with Binary Anomaly Flag Data
by Mulugeta Weldezgina Asres, Christian Walter Omlin, CMS-HCAL Collaboration
First submitted to arxiv on: 16 Dec 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Machine Learning (stat.ML)
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 This paper proposes an approach to discovering causality in anomalies detected by monitoring systems in large-scale deployments. Existing methods are limited by computational burdens, making them unsuitable for real-time use. The proposed AnomalyCD framework addresses this challenge by incorporating strategies such as anomaly flag characteristics, sparse data compression, and edge pruning adjustment approaches. The framework is validated on two datasets: a sensor data set from the Compact Muon Solenoid experiment at CERN and a public information technology monitoring dataset. Results show significant reductions in computation overhead and moderate enhancements to accuracy. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This study helps diagnose problems in complex systems by figuring out what causes unusual events to happen. Currently, finding these causes is too hard for computers to do quickly enough. The researchers came up with a new way to make this process faster and more accurate. They tested their method on data from two different sources: sensors monitoring a particle accelerator and information technology monitoring systems. Their results show that the new approach can help solve problems more efficiently. |
Keywords
» Artificial intelligence » Pruning
