https://github.com/MengjieZhao/dyedgegat

DyEdgeGAT: Dynamic Edge via Graph Attention for Early Fault Detection in IIoT Systems
https://github.com/MengjieZhao/dyedgegat

anomaly-detection gnn-algorithm machine-learning-algorithms

Last synced: 4 months ago
JSON representation

DyEdgeGAT: Dynamic Edge via Graph Attention for Early Fault Detection in IIoT Systems

• Host: GitHub
• URL: https://github.com/MengjieZhao/dyedgegat
• Owner: MengjieZhao
• License: mit
• Created: 2023-07-05T16:36:54.000Z (almost 3 years ago)
• Default Branch: main
• Last Pushed: 2025-09-10T08:56:24.000Z (9 months ago)
• Last Synced: 2025-09-10T12:08:23.419Z (9 months ago)
• Topics: anomaly-detection, gnn-algorithm, machine-learning-algorithms
• Language: Python
• Homepage: https://arxiv.org/abs/2307.03761
• Size: 28.3 KB
• Stars: 16
• Watchers: 1
• Forks: 2
• Open Issues: 1
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-multivariate-time-series-anomaly-detection-algorithms - dyedgegat

README

          
# DyEdgeGAT: Dynamic Edge via Graph Attention for Early Fault Detection in IIoT Systems

[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/dynamic-graph-attention-for-anomaly-detection/unsupervised-anomaly-detection-on-pronto)](https://paperswithcode.com/sota/unsupervised-anomaly-detection-on-pronto?p=dynamic-graph-attention-for-anomaly-detection)

Our paper has been officially accepted for publication in the **IEEE Internet of Things Journal**, and is now available online. You can access it via the following DOI link: [DOI: 10.1109/JIOT.2024.3381002](https://doi.org/10.1109/JIOT.2024.3381002).

For any questions or feedback, please open an issue in this repository or contact us directly via email.