ScholarMate
English简体中文繁體中文
客服热线:400-1616-289
登录注册
期刊论文

Concept Drift Adaptation for Time Series Anomaly Detection via Transformer

Ding, Chaoyue; Zhao, Jing*; Sun, Shiliang
NEURAL PROCESSING LETTERS2023-6DOI: 10.1007/s11063-022-11015-0
5被引9阅读
引用收藏
分享

摘要

Time series anomaly detection (TSAD) is an essential task in practical applications, such as data monitoring and network security detection. A common approach for anomaly detection is to use sequential models. As an effective sequence model, Transformer can capture the long-term dependence of the time series and is expected to better complete anomaly detection tasks. However, there are still problems to be addressed when using Transformer for anomaly detection. (1) Failing to adapt to concept drift: The vanilla Transformer assumes that the training and test data come from the same distribution. However, practical situations may often violate this assumption due to the time-varying nature of time-series data that may lead to concept drift problems. (2) High computational complexity: The time complexity of vanilla Transformer in the inference stage increase quadratically with the sequence length L. To solve the first problem, we propose the concept drift adaptation method (CDAM), a kind of distribution adaptation method, to dynamic tuning the learning rate of Transformer. CDAM aims to fully utilize the old concept data to optimize a new model on the new concept data through an online learning strategy. To address the second problem, we propose the root square sparse self-attention, which requires only O(L root L) time complexity. Experimental results on several anomaly detection benchmarks show that our model outperforms many anomaly detection methods, especially in time series with concept drift.

学科与关键词

关键词
Time series anomaly detectionTransfer learningConcept driftTransformer
相关
加载中…
  • Decompose Auto-Transformer Time Series Anomaly Detection for Network Management
    Wu, Bo; Fang, Chao*; Yao, Zhenjie; Tu, Yanhui; Chen, YixinElectronics, 2023, 12(2): 354.
  • Deep Learning for Anomaly Detection in Time-Series Data: Review, Analysis, and Guidelines
    Choi, Kukjin; Yi, Jihun; Park, Changhwa; Yoon, Sungroh*IEEE Access, 2021, 9: 120043-120065.被引 199
  • Efficient time series anomaly detection by multiresolution self-supervised discriminative network
    Huang, Desen; Shen, Lifeng; Yu, Zhongzhong; Zheng, Zhenjing; Huang, Min*; Ma, Qianli*NEUROCOMPUTING, 2022, 491: 261-272.被引 7
查看全部 →

发表信息

论文状态
公开发表
期刊
NEURAL PROCESSING LETTERS
发表日期
2023-06
卷期
第 55 卷, 第 3 期
页码
2081-2101
DOI
10.1007/s11063-022-11015-0
语言
ENGLISH
成果收录
SCIE
资助标注
NSFC [62006078, 62076096]; Shanghai Municipal Project [20511100900]; Shanghai Knowledge Service Platform Project [ZF1213]; Open Research Fund of KLATASDS-MOE; Fundamental Research Funds for the Central Universities

作者

  • D

    Ding, Chaoyue (第一作者)

  • Z

    Zhao, Jing (通讯)

查看全部 3 位作者收起作者
  • S

    Sun, Shiliang

登录解锁更多功能

  • 收藏这篇,随时在“我的 · 收藏”找回
  • 认领你的成果,生成推广素材
  • 关注作者获取最新成果
  • 加入项目组、协同写作
注册 / 登录

产品服务

  • 科研之友
  • 创新城
  • 科创云

服务支持

  • 帮助中心
  • 隐私政策
  • 服务条款

联系方式

在线客服:【】
客服热线:400-1616-289
电子邮箱:support@scholarmate.com

关注或下载科研之友

微信二维码
微信公众号
客户端下载二维码
下载客户端
科研成果科研人员科研机构科研动态爱瑞思软件

©2026 深圳市科研之友网络服务有限公司

公安备案图标粤公网安备 44030502000213
粤ICP备 16046710 号粤B2-20110417