PP: Robust Anomaly Detection for Multivariate Time Series through Stochastic Recurrent Neural Network
PROBLEM: OmniAnomaly
multivariate time series anomaly detection + unsupervised
主体思想: input: multivariate time series to RNN ------> capture the normal patterns -----> reconstruct input data by the representations ------> use the reconstruction probabilities to determine anomalies.
INTRODUCTION:
1. The first challenge is how to learn robust latent representations, considering both the temporal dependence and stochasticity of multivariate time series.
-------stochastic RNN + explicit temporal dependence among stochastic variables.
Stochastic variables are latent representations of input data and their quality is the key to model performance.
Their approach glues GRU and VAE with two key techniques:
- stochastic variable connection technique: explicitly model temporal dependence among stochastic variables in the latent space.
- Planar Normalizing Flows, which uses a series of invertible mappings可逆映射 to learn non-Gaussian posterior distributions in latent stochastic space.
2. The second challenge is how to provide interpretation to the detected entity-level anomalies, given the stochastic deep learning approaches.
Challenge: 1. capture long-term dependence. 2. capture probability distributions of multivariate time series. 3. how to interpret your results (unsupervised learning)
EVIDENCE: literature 5 shown that explicitly modeling the temporal dependence are better.
RELATED WORK:
PRELIMINARIES:
Problem statement: 以时序数据的个数作为维度,M个TS, x 属于R[M*N], x_t为一个M维的列向量,
gru, vae, and stochastic gradient variational bayes
DESIGN
OmniAnomaly structure: returns an anomaly score for x_t.
- online detection
- offline detection
- data preprocessing: data standardization, sequence segmentation through sliding windows T+1;
- input: multivariate time series inside a window, ----------Model training ------------output: an anomaly score for each observation ------- automatic threshold selection;
Detection: detect anomalies based on the reconstruction probability of x_t.
Loss function: ELBO;
Variational inference algorithms: SGVB;
Output: a univariate time series of anomaly scores
Automatic thresholds selection: extreme value theory + peaks-over-threshold;
1. use GRU to capture complex temporal dependence in x-space.
2. apply VAE to map observations to stochastic variables.
3. explicitly model temporal dependence among latent space, they propose the stochastic variable connection technique.
4. adopt planar NF.
Evaluation:
We use Precision, Recall, F1-Score (denoted as F1) to evaluate the performance of OmniAnomaly.
Baseline:
- LSTM with nonparametric dynamic thresholding
- EncDec-AD
- DAGMM
- LSTM-VAE
- Donut; 采取别的方式使donut适用于multivariate TS.
Supplementary knowledge:
1. VAE:
inference net qnet + generative net pnet.
2. GRU: gate recurrent unit
Reference
PP: Robust Anomaly Detection for Multivariate Time Series through Stochastic Recurrent Neural Network的更多相关文章
- PP: Unsupervised anomaly detection via variational auto-encoder for seasonal KPIs in web applications
Problem: unsupervised anomaly detection for seasonal KPIs in web applications. Donut: an unsupervise ...
- PP: A dual-stage attention-based recurrent neural network for time series prediction
Problem: time series prediction The nonlinear autoregressive exogenous model: The Nonlinear autoregr ...
- "Regressing Robust and Discriminative 3D Morphable Models with a very Deep Neural Network" 解读
简介:这是一篇17年的CVPR,作者提出使用现有的人脸识别深度神经网络Resnet101来得到一个具有鲁棒性的人脸模型. 原文链接:https://www.researchgate.net/publi ...
- Anomaly Detection for Time Series Data with Deep Learning——本质分类正常和异常的行为,对于检测异常行为,采用预测正常行为方式来做
A sample network anomaly detection project Suppose we wanted to detect network anomalies with the un ...
- Machine Learning No.10: Anomaly detection
1. Algorithm 2. evaluating an anomaly detection system 3. anomaly detection vs supervised learning 4 ...
- PP: Time series anomaly detection with variational autoencoders
Problem: unsupervised anomaly detection Model: VAE-reEncoder VAE with two encoders and one decoder. ...
- Time Series Anomaly Detection
这里有个2015年的综述文章,概括的比较好,各种技术的适用场景. https://iwringer.wordpress.com/2015/11/17/anomaly-detection-concep ...
- PP: Deep r -th Root of Rank Supervised Joint Binary Embedding for Multivariate Time Series Retrieval
from: Dacheng Tao 悉尼大学 PROBLEM: time series retrieval: given the current multivariate time series se ...
- PP: Toeplitz Inverse Covariance-Based Clustering of Multivariate Time Series Data
From: Stanford University; Jure Leskovec, citation 6w+; Problem: subsequence clustering. Challenging ...
随机推荐
- MySQL 什么是事务?
该文为< MySQL 实战 45 讲>的学习笔记,感谢查看,如有错误,欢迎指正 一.事务简介 事务就是为了保证一组数据库操作,要么全部成功,要么全部失败. 事务是在引擎层实现的,也就是说并 ...
- deepin系统修改IP地址记录
今天在配置软路由的时候需要设备有线网卡为静态地址,于是便按照如下方法进行修改: 1.备份网络配置文件: sudo cp /etc/network/interfaces /etc/netword/int ...
- 02-flink时间语义 与 Window 基础概念与实现原理
Flink 多种时间语义对比 Flink 在流应用程序中支持不同的 Time 概念,就比如有 Processing Time.Event Time 和 Ingestion Time.下面我们一起来看看 ...
- Node.js文档-path
用于处理文件路径和目录路径 引入 const path = require('path') path.extname(path) 返回扩展名.从最后一次出现 . 字符到字符串结束. const pat ...
- FPGA分频与倍频的简单总结(涉及自己设计,调用时钟IP核,调用MMCM原语模块)
原理介绍 1.分频 FPGA设计中时钟分频是重要的基础知识,对于分频通常是利用计数器来实现想要的时钟频率,由此可知分频后的频率周期更大.一般而言实现偶数系数的分频在程序设计上较为容易,而奇数分频则相对 ...
- js获取时间及转化
有关Javascript的本地时间获取,下面我直接用代码来进行举例吧 let time = new Date(); let month = time.getMonth()+1; //获取的月份0~11 ...
- Qt的qDebug()改写为cout
经常用c++,qDebug()用的不习惯,将其改为cout,并且为了方便调试,还添加了文件名及行号. 代码如下: // __FILE__文件名,__LINE__行号,如果想看时间还可以添加__TIME ...
- Kemaswill 机器学习 数据挖掘 推荐系统 Python optparser模块简介
Python optparser模块简介
- 字符串相等 impossible 1480
题目描述 两个长度不超过80的字符串,串中包括大写.小写和空格字符,去掉空格并忽略大小写后,判断两个字符串是否相等. 输入描述 第1行输入是测试数据的组数n,每组测试数据占两行,第1行是第一个字符串s ...
- pyqt5-下拉框联动效果
from PyQt5.Qt import * class MyWindow(QWidget): def __init__(self): super().__init__() self.setWindo ...