Deep Contrastive One-Class Time Series Anomaly Detection

被引:0
|
作者
Wang, Rui [1 ]
Liu, Chongwei [1 ]
Mou, Xudong [1 ]
Gao, Kai [2 ]
Guo, Xiaohui [3 ]
Liu, Pin [4 ]
Wo, Tianyu [5 ]
Liu, Xudong [1 ,3 ]
机构
[1] Beihang Univ, Sch Comp Sci & Engn, Beijing, Peoples R China
[2] Univ New South Wales, Sydney, NSW, Australia
[3] Beihang Univ, Hangzhou Innovat Inst, Hangzhou, Peoples R China
[4] China Univ Geosci Beijing, Sch Informat Engn, Beijing, Peoples R China
[5] Beihang Univ, Coll Software, Beijing, Peoples R China
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The accumulation of time-series data and the absence of labels make time-series Anomaly Detection (AD) a self-supervised deep learning task. Single-normality-assumption-based methods, which reveal only a certain aspect of the whole normality, are incapable of tasks involved with a large number of anomalies. Specifically, Contrastive Learning (CL) methods distance negative pairs, many of which consist of both normal samples, thus reducing the AD performance. Existing multi-normality-assumption-based methods are usually two-staged, firstly pre-training through certain tasks whose target may differ from AD, limiting their performance. To overcome the shortcomings, a deep Contrastive One-Class Anomaly detection method of time series (COCA) is proposed by authors, following the normality assumptions of CL and one-class classification. It treats the original and reconstructed representations as the positive pair of negative-sample-free CL, namely "sequence contrast". Next, invariance terms and variance terms compose a contrastive one-class loss function in which the loss of the assumptions is optimized by invariance terms simultaneously and the "hypersphere collapse" is prevented by variance terms. In addition, extensive experiments on two real-world time-series datasets show the superior performance of the proposed method achieves state-of-the-art.
引用
收藏
页码:694 / 702
页数:9
相关论文
共 50 条
  • [41] Time-series novelty detection using one-class support vector machines
    Ma, JS
    Perkins, S
    PROCEEDINGS OF THE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS 2003, VOLS 1-4, 2003, : 1741 - 1745
  • [42] Anomaly Detection via Reverse Distillation from One-Class Embedding
    Deng, Hanqiu
    Li, Xingyu
    2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2022, : 9727 - 9736
  • [43] Anomaly Detection in Lexical Definitions via One-Class Classification Techniques
    Jumpathong, Sawittree
    Kriengket, Kanyanut
    Boonkwan, Prachya
    Supnithi, Thepchai
    16TH INTERNATIONAL JOINT SYMPOSIUM ON ARTIFICIAL INTELLIGENCE AND NATURAL LANGUAGE PROCESSING (ISAI-NLP 2021), 2021,
  • [44] One-class graph neural networks for anomaly detection in attributed networks
    Xuhong Wang
    Baihong Jin
    Ying Du
    Ping Cui
    Yingshui Tan
    Yupu Yang
    Neural Computing and Applications, 2021, 33 : 12073 - 12085
  • [45] Unsupervised Anomaly Detection Based on Clustering and Multiple One-Class SVM
    Song, Jungsuk
    Takakura, Hiroki
    Okabe, Yasuo
    Kwon, Yongjin
    IEICE TRANSACTIONS ON COMMUNICATIONS, 2009, E92B (06) : 1981 - 1990
  • [46] Localized Multiple Kernel learning for Anomaly Detection: One-class Classification
    Gautam, Chandan
    Balaji, Ramesh
    Sudharsan, K.
    Tiwari, Aruna
    Ahuja, Kapil
    KNOWLEDGE-BASED SYSTEMS, 2019, 165 : 241 - 252
  • [47] One-Class Collective Anomaly Detection Based on LSTM-RNNs
    Nga Nguyen Thi
    Van Loi Cao
    Nhien-An Le-Khac
    TRANSACTIONS ON LARGE-SCALE DATA- AND KNOWLEDGECENTERED SYSTEMS XXXVI: SPECIAL ISSUE ON DATA AND SECURITY ENGINEERING, 2018, 10720 : 73 - 85
  • [48] Backdoor Attack Against One-Class Sequential Anomaly Detection Models
    Cheng, He
    Yuan, Shuhan
    ADVANCES IN KNOWLEDGE DISCOVERY AND DATA MINING, PT III, PAKDD 2024, 2024, 14647 : 262 - 274
  • [49] New Perspective on Progressive GANs Distillation for One-class Anomaly Detection
    Dong, Yu
    Zhang, Zhiwei
    Peng, Hanyu
    Chen, Shifeng
    JOURNAL OF IMAGING SCIENCE AND TECHNOLOGY, 2023, 67 (06)
  • [50] Local density one-class support vector machines for anomaly detection
    Tian, Jiang
    Gu, Hong
    Gao, Chiyang
    Lian, Jie
    NONLINEAR DYNAMICS, 2011, 64 (1-2) : 127 - 130