Forecast-based Multi-aspect Framework for Multivariate Time-series Anomaly Detection

被引:1
作者
Wang, Lan [1 ]
Lin, Yusan [1 ]
Wu, Yuhang [1 ]
Chen, Huiyuan [1 ]
Wang, Fei [1 ]
Yang, Hao [1 ]
机构
[1] Visa Res, Palo Alto, CA 94306 USA
来源
2021 IEEE INTERNATIONAL CONFERENCE ON BIG DATA (BIG DATA) | 2021年
关键词
Anomaly Detection; Multivariate Time Series; Unsupervised Learning;
D O I
10.1109/BigData52589.2021.9671776
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Today's cyber-world is vastly multivariate. Metrics collected at extreme varieties demand multivariate algorithms to properly detect anomalies. However, forecast-based algorithms, as widely proven approaches, often perform sub-optimally or inconsistently across datasets. A key common issue is they strive to be one-size-fits-all but anomalies are distinctive in nature. We propose a method that tailors to such distinction. Presenting FMUAD - a Forecast-based, Multi-aspect, Unsupervised Anomaly Detection framework. FMUAD explicitly and separately captures the signature traits of anomaly types - spatial change, temporal change and correlation change - with independent modules. The modules then jointly learn an optimal feature representation, which is highly flexible and intuitive, unlike most other models in the category. Extensive experiments show our FMUAD framework consistently outperforms other state-of-the-art forecast-based anomaly detectors.
引用
收藏
页码:938 / 947
页数:10
相关论文
共 50 条
  • [41] Asymptotic Consistent Graph Structure Learning for Multivariate Time-Series Anomaly Detection
    Pang, Huaxin
    Wei, Shikui
    Li, Youru
    Liu, Ting
    Zhang, Huaqi
    Qin, Ying
    Zhao, Yao
    IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2024, 73 : 1 - 10
  • [42] Graph-Attention Diffusion for Enhanced Multivariate Time-Series Anomaly Detection
    Lanko, Vadim
    Makarov, Ilya
    IEEE OPEN JOURNAL OF THE INDUSTRIAL ELECTRONICS SOCIETY, 2024, 5 : 1353 - 1364
  • [43] Anomaly Detection Method for Multivariate Time Series Data Based on BLTranAD
    Zhang, Chuanlei
    Wu, Songlin
    Gao, Ming
    Li, Yubo
    Shi, Gongcheng
    Li, Yicong
    Ma, Hui
    ADVANCED INTELLIGENT COMPUTING TECHNOLOGY AND APPLICATIONS, PT XIII, ICIC 2024, 2024, 14874 : 16 - 26
  • [44] Industrial multivariate time-series data anomaly detection incorporating attention mechanisms and adversarial training
    Yang, Wenjie
    Chu, Wenchao
    Wu, Xingfu
    Zhou, Lianlin
    Wang, Jiayi
    Yang, Hua
    Li, Zirui
    INTERNATIONAL JOURNAL OF COMPUTER INTEGRATED MANUFACTURING, 2025,
  • [45] UNSUPERVISED ANOMALY DETECTION FOR MULTIVARIATE TIME SERIES USING DIFFUSION MODEL
    Hu, Rongyao
    Yuan, Xinyu
    Qiao, Yan
    Zhang, BenChu
    Zhao, Pei
    2024 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2024), 2024, : 9606 - 9610
  • [46] Unsupervised Anomaly Detection Approach for Multivariate Time Series
    Zhou, Yuanlin
    Song, Yingxuan
    Qian, Mideng
    2021 21ST INTERNATIONAL CONFERENCE ON SOFTWARE QUALITY, RELIABILITY AND SECURITY COMPANION (QRS-C 2021), 2021, : 229 - 235
  • [47] An Evaluation of Time-Series Anomaly Detection in Computer Networks
    Nguyen, Hong
    Hajisafi, Arash
    Abdoli, Alireza
    Kim, Seon Ho
    Shahabi, Cyrus
    2023 INTERNATIONAL CONFERENCE ON INFORMATION NETWORKING, ICOIN, 2023, : 104 - 109
  • [48] DCFF-MTAD: A Multivariate Time-Series Anomaly Detection Model Based on Dual-Channel Feature Fusion
    Xu, Zheng
    Yang, Yumeng
    Gao, Xinwen
    Hu, Min
    SENSORS, 2023, 23 (08)
  • [49] Contrastive autoencoder for anomaly detection in multivariate time series
    Zhou, Hao
    Yu, Ke
    Zhang, Xuan
    Wu, Guanlin
    Yazidi, Anis
    INFORMATION SCIENCES, 2022, 610 : 266 - 280
  • [50] A Multi-scale Parallel Unsupervised Model for Multivariate Time Series Anomaly Detection
    Bao, Junpeng
    Gao, Han
    Zhang, Chengpu
    Jia, Wentao
    Gao, Junzhe
    Yang, Tongzhi
    ARTIFICIAL INTELLIGENCE APPLICATIONS AND INNOVATIONS, PT IV, AIAI 2024, 2024, 714 : 241 - 251