PAFormer: Anomaly Detection of Time Series With Parallel-Attention Transformer

计算机科学 异常检测 规范化(社会学) 人工智能 数据挖掘 变压器 数据点 机器学习 模式识别(心理学) 工程类 电压 社会学 人类学 电气工程
作者
Ningning Bai,Xiaofeng Wang,Ruidong Han,Q. Wang,Zinian Liu
出处
期刊:IEEE transactions on neural networks and learning systems [Institute of Electrical and Electronics Engineers]
卷期号:36 (2): 3315-3328 被引量:5
标识
DOI:10.1109/tnnls.2023.3337876
摘要

Time-series anomaly detection is a critical task with significant impact as it serves a pivotal role in the field of data mining and quality management. Current anomaly detection methods are typically based on reconstruction or forecasting algorithms, as these methods have the capability to learn compressed data representations and model time dependencies. However, most methods rely on learning normal distribution patterns, which can be difficult to achieve in real-world engineering applications. Furthermore, real-world time-series data is highly imbalanced, with a severe lack of representative samples for anomalous data, which can lead to model learning failure. In this article, we propose a novel end-to-end unsupervised framework called the parallel-attention transformer (PAFormer), which discriminates anomalies by modeling both the global characteristics and local patterns of time series. Specifically, we construct parallel-attention (PA), which includes two core modules: the global enhanced representation module (GERM) and the local perception module (LPM). GERM consists of two pattern units and a normalization module, with attention weights that indicate the relationship of each data point to the whole series (global). Due to the rarity of anomalous points, they have strong associations with adjacent data points. LPM is composed of a learnable Laplace kernel function that learns the neighborhood relevancies through the distributional properties of the kernel function (local). We employ the PA to learn the global-local distributional differences for each data point, which enables us to discriminate anomalies. Finally, we propose a two-stage adversarial loss to optimize the model. We conduct experiments on five public benchmark datasets (real-world datasets) and one synthetic dataset. The results show that PAFormer outperforms state-of-the-art baselines.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
CAOHOU应助论文顺利采纳,获得10
刚刚
nancy93228完成签到 ,获得积分10
1秒前
搜集达人应助JW采纳,获得10
3秒前
???完成签到,获得积分10
5秒前
优秀的白曼完成签到,获得积分10
7秒前
王小西发布了新的文献求助10
8秒前
碧蓝莫言完成签到 ,获得积分10
10秒前
清璃完成签到 ,获得积分10
11秒前
虚心的寒梦完成签到,获得积分10
11秒前
秋秋发布了新的文献求助10
11秒前
kkk完成签到,获得积分10
13秒前
bnhh完成签到,获得积分10
13秒前
Betty应助lindahuang采纳,获得10
14秒前
ilk666完成签到,获得积分10
15秒前
小王同学发布了新的文献求助10
15秒前
奶油布丁完成签到,获得积分10
18秒前
酶没美镁完成签到,获得积分10
18秒前
天天快乐应助李治海采纳,获得10
19秒前
星辰大海应助lll采纳,获得10
19秒前
龙1完成签到,获得积分10
19秒前
yzhilson完成签到 ,获得积分10
20秒前
量子星尘发布了新的文献求助10
21秒前
RRR完成签到,获得积分10
22秒前
金色天际线完成签到,获得积分10
23秒前
明ming到此一游完成签到 ,获得积分10
26秒前
pophoo完成签到,获得积分10
26秒前
11发布了新的文献求助10
27秒前
酷炫的黄豆完成签到 ,获得积分10
28秒前
hzz完成签到,获得积分10
31秒前
32秒前
深情安青应助科研通管家采纳,获得10
32秒前
fang应助科研通管家采纳,获得10
32秒前
Passskd发布了新的文献求助10
32秒前
fang应助科研通管家采纳,获得10
32秒前
32秒前
32秒前
32秒前
彭于晏应助科研通管家采纳,获得10
32秒前
山野村夫应助科研通管家采纳,获得10
32秒前
Singularity应助科研通管家采纳,获得10
32秒前
高分求助中
【提示信息,请勿应助】关于scihub 10000
Les Mantodea de Guyane: Insecta, Polyneoptera [The Mantids of French Guiana] 3000
徐淮辽南地区新元古代叠层石及生物地层 3000
The Mother of All Tableaux: Order, Equivalence, and Geometry in the Large-scale Structure of Optimality Theory 3000
Handbook of Industrial Diamonds.Vol2 1100
Global Eyelash Assessment scale (GEA) 1000
Picture Books with Same-sex Parented Families: Unintentional Censorship 550
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 4038303
求助须知:如何正确求助?哪些是违规求助? 3576013
关于积分的说明 11374210
捐赠科研通 3305780
什么是DOI,文献DOI怎么找? 1819322
邀请新用户注册赠送积分活动 892672
科研通“疑难数据库(出版商)”最低求助积分说明 815029