RobustTAD: Robust Time Series Anomaly Detection via Decomposition and Convolutional Neural Networks

The monitoring and management of numerous and diverse time series data at Alibaba Group calls for an effective and scalable time series anomaly detection service. In this paper, we propose RobustTAD, a Robust Time series Anomaly Detection framework by integrating robust seasonal-trend decomposition and convolutional neural network for time series data. The seasonal-trend decomposition can effectively handle complicated patterns in time series, and meanwhile significantly simplifies the architecture of the neural network, which is an encoder-decoder architecture with skip connections. This architecture can effectively capture the multi-scale information from time series, which is very useful in anomaly detection. Due to the limited labeled data in time series anomaly detection, we systematically investigate data augmentation methods in both time and frequency domains. We also introduce label-based weight and value-based weight in the loss function by utilizing the unbalanced nature of the time series anomaly detection problem. Compared with the widely used forecasting-based anomaly detection algorithms, decomposition-based algorithms, traditional statistical algorithms, as well as recent neural network based algorithms, RobustTAD performs significantly better on public benchmark datasets. It is deployed as a public online service and widely adopted in different business scenarios at Alibaba Group.

[1]  M. Otto,et al.  Outliers in Time Series , 1972 .

[2]  Subutai Ahmad,et al.  Evaluating Real-Time Anomaly Detection Algorithms -- The Numenta Anomaly Benchmark , 2015, 2015 IEEE 14th International Conference on Machine Learning and Applications (ICMLA).

[3]  Weinan Wang,et al.  Online FDR Controlled Anomaly Detection for Streaming Time Series , 2022 .

[4]  Rob J. Hyndman,et al.  STR: A Seasonal-Trend Decomposition Procedure Based on Regression , 2015 .

[5]  Dana Kulic,et al.  Data augmentation of wearable sensor data for parkinson’s disease monitoring using convolutional neural networks , 2017, ICMI.

[6]  Gwilym M. Jenkins,et al.  Time series analysis, forecasting and control , 1971 .

[7]  Sunav Choudhary,et al.  Sparse Decomposition for Time Series Forecasting and Anomaly Detection , 2018, SDM.

[8]  Yingying Zhang,et al.  RobustPeriod: Robust Time-Frequency Mining for Multiple Periodicity Detection , 2020, SIGMOD Conference.

[9]  Rob J Hyndman,et al.  Forecasting Time Series With Complex Seasonal Patterns Using Exponential Smoothing , 2011 .

[10]  Irma J. Terpenning,et al.  STL : A Seasonal-Trend Decomposition Procedure Based on Loess , 1990 .

[11]  Xiaomin Song,et al.  Time Series Data Augmentation for Deep Learning: A Survey , 2020, ArXiv.

[12]  Xiaomin Song,et al.  RobustTrend: A Huber Loss with a Combined First and Second Order Difference Regularization for Time Series Trend Filtering , 2019, IJCAI.

[13]  Philip S. Yu,et al.  On Periodicity Detection and Structural Periodic Similarity , 2005, SDM.

[14]  R. Tibshirani.  Adaptive piecewise polynomial estimation via trend filtering , 2013, 1304.2986.

[15]  Arun Kejariwal,et al.  A Novel Technique for Long-Term Anomaly Detection in the Cloud , 2014, HotCloud.

[16]  Patrick Flandrin,et al.  Trend Filtering: Empirical Mode Decompositions versus ℓ1 and Hodrick-Prescott , 2011, Adv. Data Sci. Adapt. Anal..

[17]  Arun Kejariwal,et al.  Automatic Anomaly Detection in the Cloud Via Statistical Learning , 2017, ArXiv.

[18]  Germain Forestier,et al.  Data augmentation using synthetic data for time series classification with deep residual networks , 2018, ArXiv.

[19]  Sudipto Guha,et al.  Robust Random Cut Forest Based Anomaly Detection on Streams , 2016, ICML.

[20]  Xiaoli Li,et al.  Deep Convolutional Neural Networks on Multichannel Time Series for Human Activity Recognition , 2015, IJCAI.

[21]  Bo Zong,et al.  A Deep Neural Network for Unsupervised Anomaly Detection and Diagnosis in Multivariate Time Series Data , 2018, AAAI.

[22]  Jeffrey Scott Vitter,et al.  Mining deviants in time series data streams , 2004, Proceedings. 16th International Conference on Scientific and Statistical Database Management, 2004..

[23]  Taghi M. Khoshgoftaar,et al.  A survey on Image Data Augmentation for Deep Learning , 2019, Journal of Big Data.

[24]  Charu C. Aggarwal,et al.  Outlier Detection for Temporal Data: A Survey , 2014, IEEE Transactions on Knowledge and Data Engineering.

[25]  Valentino Constantinou,et al.  Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholding , 2018, KDD.

[26]  Roman Kern,et al.  SAZED: parameter-free domain-agnostic season length estimation in time series data , 2019, Data Mining and Knowledge Discovery.

[27]  Zhuowen Tu,et al.  Deeply Supervised Salient Object Detection with Short Connections , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[28]  Ross B. Girshick,et al.  Mask R-CNN , 2017, 1703.06870.

[29]  Tailai Wen,et al.  Time Series Anomaly Detection Using Convolutional Neural Networks and Transfer Learning , 2019, ArXiv.

[30]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[31]  Arun Kejariwal,et al.  On the Runtime-Efficacy Trade-off of Anomaly Detection Techniques for Real-Time Streaming Data , 2017, ArXiv.

[32]  Guokun Lai,et al.  Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks , 2017, SIGIR.

[33]  Howon Kim,et al.  Long Short Term Memory Recurrent Neural Network Classifier for Intrusion Detection , 2016, 2016 International Conference on Platform Technology and Service (PlatCon).

[34]  Pierre Kornprobst,et al.  Bilateral Filtering , 2009 .

[35]  Wei Sun,et al.  Robust Anomaly Detection for Multivariate Time Series through Stochastic Recurrent Neural Network , 2019, KDD.

[36]  Julien Cohen-Adad,et al.  Deep semantic segmentation of natural and medical images: a review , 2019, Artificial Intelligence Review.

[37]  Hui Ye,et al.  An adaptive approach for anomaly detector selection and fine-tuning in time series , 2019, Proceedings of the 1st International Workshop on Deep Learning Practice for High-Dimensional Sparse Data.

[38]  Subutai Ahmad,et al.  Unsupervised real-time anomaly detection for streaming data , 2017, Neurocomputing.

[39]  Saeed Amizadeh,et al.  Generic and Scalable Framework for Automated Time-series Anomaly Detection , 2015, KDD.

[40]  Yang Feng,et al.  Unsupervised Anomaly Detection via Variational Auto-Encoder for Seasonal KPIs in Web Applications , 2018, WWW.

[41]  Chao Yi,et al.  Time-Series Anomaly Detection Service at Microsoft , 2019, KDD.

[42]  Sanjay Chawla,et al.  Mining for Outliers in Sequential Databases , 2006, SDM.

[43]  Sanjeev Khudanpur,et al.  Audio augmentation for speech recognition , 2015, INTERSPEECH.

[44]  Zhe Zhang,et al.  Fast RobustSTL: Efficient and Robust Seasonal-Trend Decomposition for Time Series with Complex Patterns , 2020, KDD.

[45]  Alexandre Termier,et al.  Anomaly Detection in Streams with Extreme Value Theory , 2017, KDD.

[46]  Lovekesh Vig,et al.  Long Short Term Memory Networks for Anomaly Detection in Time Series , 2015, ESANN.

[47]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[48]  P. Young,et al.  Time series analysis, forecasting and control , 1972, IEEE Transactions on Automatic Control.

[49]  Kristian Kersting,et al.  Stochastic Online Anomaly Analysis for Streaming Time Series , 2017, IJCAI.

[50]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[51]  VARUN CHANDOLA,et al.  Anomaly detection: A survey , 2009, CSUR.

[52]  Eamonn J. Keogh,et al.  Finding surprising patterns in a time series database in linear time and space , 2002, KDD.

[53]  Xiaomin Song,et al.  RobustSTL: A Robust Seasonal-Trend Decomposition Algorithm for Long Time Series , 2018, AAAI.