METER: A Dynamic Concept Adaptation Framework for Online Anomaly Detection

被引:0
|
作者
Zhu, Jiaqi [1 ]
Cai, Shaofeng [2 ]
Deng, Fang [1 ]
Ooi, Beng Chin [2 ]
Zhang, Wenqiao [3 ]
机构
[1] Beijing Inst Technol, Beijing, Peoples R China
[2] Natl Univ Singapore, Singapore, Singapore
[3] Zhejiang Univ, Hangzhou, Zhejiang, Peoples R China
来源
PROCEEDINGS OF THE VLDB ENDOWMENT | 2023年 / 17卷 / 04期
基金
新加坡国家研究基金会; 中国国家自然科学基金;
关键词
OUTLIER DETECTION; TIME; MODEL;
D O I
10.14778/3636218.3636233
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Real-time analytics and decision-making require online anomaly detection (OAD) to handle drifts in data streams efficiently and effectively. Unfortunately, existing approaches are often constrained by their limited detection capacity and slow adaptation to evolving data streams, inhibiting their efficacy and efficiency in handling concept drift, which is a major challenge in evolving data streams. In this paper, we introduce METER, a novel dynamic concept adaptation framework that introduces a new paradigm for OAD. METER addresses concept drift by first training a base detection model on historical data to capture recurring central concepts, and then learning to dynamically adapt to new concepts in data streams upon detecting concept drift. Particularly, METER employs a novel dynamic concept adaptation technique that leverages a hypernetwork to dynamically generate the parameter shift of the base detection model, providing a more effective and efficient solution than conventional retraining or fine-tuning approaches. Further, METER incorporates a lightweight drift detection controller, underpinned by evidential deep learning, to support robust and interpretable concept drift detection. We conduct an extensive experimental evaluation, and the results show that METER significantly outperforms existing OAD approaches in various application scenarios.
引用
收藏
页码:794 / 807
页数:14
相关论文
共 50 条
  • [1] Online Anomaly Detection with Concept Drift Adaptation using Recurrent Neural Networks
    Saurav, Sakti
    Malhotra, Pankaj
    Tv, Vishnu
    Gugulothu, Narendhar
    Vig, Lovekesh
    Agarwal, Puneet
    Shroff, Gautam
    [J]. PROCEEDINGS OF THE ACM INDIA JOINT INTERNATIONAL CONFERENCE ON DATA SCIENCE AND MANAGEMENT OF DATA (CODS-COMAD'18), 2018, : 78 - 87
  • [2] Addressing Concept Drift in IoT Anomaly Detection: Drift Detection, Interpretation, and Adaptation
    Xu L.
    Han Z.
    Zhao D.
    Li X.
    Yu F.
    Chen C.
    [J]. IEEE Transactions on Sustainable Computing, 2024, 9 (06): : 1 - 12
  • [3] Scalable prediction-based online anomaly detection for smart meter data
    Liu, Xiufeng
    Nielsen, Per Sieverts
    [J]. INFORMATION SYSTEMS, 2018, 77 : 34 - 47
  • [4] ONLINE ANOMALY DETECTION IN VIDEOS BY CLUSTERING DYNAMIC EXEMPLARS
    Feng, Jie
    Zhang, Chao
    Hao, Pengwei
    [J]. 2012 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP 2012), 2012, : 3097 - 3100
  • [5] An anomaly detection framework for dynamic systems using a Bayesian hierarchical framework
    Moghaddass, Ramin
    Sheng, Shuangwen
    [J]. APPLIED ENERGY, 2019, 240 : 561 - 582
  • [6] Concept Drift Adaptation for Time Series Anomaly Detection via Transformer
    Ding, Chaoyue
    Zhao, Jing
    Sun, Shiliang
    [J]. NEURAL PROCESSING LETTERS, 2023, 55 (03) : 2081 - 2101
  • [7] Concept Drift Adaptation for Time Series Anomaly Detection via Transformer
    Chaoyue Ding
    Jing Zhao
    Shiliang Sun
    [J]. Neural Processing Letters, 2023, 55 : 2081 - 2101
  • [8] Unsupervised Online Anomaly Detection With Parameter Adaptation for KPI Abrupt Changes
    Yu, Guang
    Cai, Zhiping
    Wang, Siqi
    Chen, Haiwen
    Liu, Fang
    Liu, Anfeng
    [J]. IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT, 2020, 17 (03): : 1294 - 1308
  • [9] Concept Drift Adaption for Online Anomaly Detection in Structural Health Monitoring
    Tian, Hongda
    Nguyen Lu Dang Khoa
    Anaissi, Ali
    Wang, Yang
    Chen, Fang
    [J]. PROCEEDINGS OF THE 28TH ACM INTERNATIONAL CONFERENCE ON INFORMATION & KNOWLEDGE MANAGEMENT (CIKM '19), 2019, : 2813 - 2821
  • [10] Symbolic Dynamic Filtering for Online Power Quality Anomaly Detection
    Saxena, Kritika
    Gurrala, Gurunath
    Joseph, Francis C.
    Teja, Balla Ravi
    [J]. 2020 IEEE POWER & ENERGY SOCIETY GENERAL MEETING (PESGM), 2020,