[CIKM'23] DuoGAT: Dual Time-oriented Graph Attention Networks for Accurate, Efficient and Explainable Anomaly Detection on Time-series

This repository provides the official implementation of DuoGAT: Dual Time-oriented Graph Attention Networks for Accurate, Efficient and Explainable Anomaly Detection on Time-series, which was accepted at CIKM 2023. Paper

Overview

Main results

Citation

@inproceedings{lee2023duogat,
  title={Duogat: Dual time-oriented graph attention networks for accurate, efficient and explainable anomaly detection on time-series},
  author={Lee, Jongsoo and Park, Byeongtae and Chae, Dong-Kyu},
  booktitle={Proceedings of the 32nd ACM International Conference on Information and Knowledge Management},
  pages={1188--1197},
  year={2023}
}

License

This project is licensed under the MIT License. See the LICENSE file for details.