skip to main content
10.1145/3442381.3450013acmconferencesArticle/Chapter ViewAbstractPublication PagesthewebconfConference Proceedingsconference-collections
research-article

SDFVAE: Static and Dynamic Factorized VAE for Anomaly Detection of Multivariate CDN KPIs

Published: 03 June 2021 Publication History

Editorial Notes

The authors have requested minor, non-substantive changes to the VoR and, in accordance with ACM policies, a Corrected VoR was published on March 15, 2022. For reference purposes the VoR may still be accessed via the Supplemental Material section on this page.

Abstract

Content Delivery Networks (CDNs) are critical for providing good user experience of cloud services. CDN providers typically collect various multivariate Key Performance Indicators (KPIs) time series to monitor and diagnose system performance. State-of-the-art anomaly detection methods mostly use deep learning to extract the normal patterns of data, due to its superior performance. However, KPI data usually exhibit non-additive Gaussian noise, which makes it difficult for deep learning models to learn the normal patterns, resulting in degraded performance in anomaly detection. In this paper, we propose a robust and noise-resilient anomaly detection mechanism using multivariate KPIs. Our key insight is that different KPIs are constrained by certain time-invariant characteristics of the underlying system, and that explicitly modelling such invariance may help resist noise in the data. We thus propose a novel anomaly detection method called SDFVAE, short for Static and Dynamic Factorized VAE, that learns the representations of KPIs by explicitly factorizing the latent variables into dynamic and static parts. Extensive experiments using real-world data show that SDFVAE achieves a F1-score ranging from 0.92 to 0.99 on both regular and noisy dataset, outperforming state-of-the-art methods by a large margin.

Supplementary Material

3450013-vor (3450013-vor.pdf)
Version of Record for "SDFVAE: Static and Dynamic Factorized VAE for Anomaly Detection of Multivariate CDN KPIs" by Dai et al., Proceedings of the Web Conference 2021 (WWW '21).

References

[1]
Jinwon An and Sungzoon Cho. 2015. Variational Autoencoder based Anomaly Detection using Reconstruction Probability. Technical Report. SNU Data Mining Center(2015), 1–8.
[2]
Julien Audibert, Pietro Michiardi, Frédéric Guyard, Sébastien Marti, and Maria A. Zuluaga. 2020. USAD: UnSupervised Anomaly Detection on Multivariate Time Series. In ACM SIGKDD 2020. 3395–3404.
[3]
Philip Becker-Ehmck, Jan Peters, and Patrick van der Smagt. 2019. Switching Linear Dynamics for Variational Bayes Filtering. In ICML 2019. 553–562.
[4]
Ashish Bora, Eric Price, and Alexandros G. Dimakis. 2018. AmbientGAN: Generative models from lossy measurements. In ICLR 2018.
[5]
Wenxiao Chen, Haowen Xu, Zeyan Li, Dan Pei, Jie Chen, Honglin Qiao, Yang Feng, and Zhaogang Wang. 2019. Unsupervised Anomaly Detection for Intricate KPIs via Adversarial Training of VAE. In IEEE INFOCOM 2019. 1891–1899.
[6]
Yingying Chen, Ratul Mahajan, Baskar Sridharan, and Zhi-Li Zhang. 2013. A provider-side view of web search response time. In ACM SIGCOMM 2013.
[7]
Kyunghyun Cho, Bart van Merrienboer, Çaglar Gülçehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio. 2014. Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation. In EMNLP 2014. 1724–1734.
[8]
Junyoung Chung, Kyle Kastner, Laurent Dinh, Kratarth Goel, Aaron C. Courville, and Yoshua Bengio. 2015. A Recurrent Latent Variable Model for Sequential Data. In NIPS 2015. 2980–2988.
[9]
Jesse Davis and Mark Goadrich. 2006. The relationship between Precision-Recall and ROC curves. In ICML 2006, Vol. 148. 233–240.
[10]
Emily L. Denton and Vighnesh Birodkar. 2017. Unsupervised Learning of Disentangled Representations from Video. In NIPS 2017.
[11]
Steven Diamond, Vincent Sitzmann, Stephen P. Boyd, Gordon Wetzstein, and Felix Heide. 2017. Dirty Pixels: Optimizing Image Classification Architectures for Raw Sensor Data. arxiv:1701.06487
[12]
Marco Fraccaro, Søren Kaae Sønderby, Ulrich Paquet, and Ole Winther. 2016. Sequential Neural Models with Stochastic Layers. In NIPS 2016. 2199–2207.
[13]
Alex Graves and Jürgen Schmidhuber. 2005. Framewise phoneme classification with bidirectional LSTM and other neural network architectures. Neural Networks 18(2005), 602–610.
[14]
David Hallac, Sagar Vare, Stephen P. Boyd, and Jure Leskovec. 2017. Toeplitz Inverse Covariance-Based Clustering of Multivariate Time Series Data. In ACM SIGKDD 2017. 215–223.
[15]
Wei-Ning Hsu, Yu Zhang, and James R. Glass. 2017. Unsupervised Learning of Disentangled and Interpretable Representations from Sequential Data. In NIPS 2017. 1878–1889.
[16]
Kyle Hundman, Valentino Constantinou, Christopher Laporte, Ian Colwell, and Tom Söderström. 2018. Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholding. In ACM SIGKDD 2018. 387–395.
[17]
Guofei Jiang, Haifeng Chen, and Kenji Yoshihira. 2007. Efficient and Scalable Algorithms for Inferring Likely Invariants in Distributed Systems. IEEE Trans. Knowl. Data Eng. 19 (2007), 1508–1523.
[18]
Takuhiro Kaneko and Tatsuya Harada. 2020. Noise Robust Generative Adversarial Networks. In IEEE/CVF CVPR 2020. 8401–8411.
[19]
Diederik P. Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In ICLR 2015.
[20]
Diederik P. Kingma and Max Welling. 2014. Auto-Encoding Variational Bayes. In ICLR 2014.
[21]
Dan Li, Dacheng Chen, Baihong Jin, Lei Shi, Jonathan Goh, and See-Kiong Ng. 2019. MAD-GAN: Multivariate Anomaly Detection for Time Series Data with Generative Adversarial Networks. In Artificial Neural Networks and Machine Learning - ICANN. 703–716.
[22]
Yingzhen Li and Stephan Mandt. 2018. Disentangled Sequential Autoencoder. In ICML 2018. 5656–5665.
[23]
Dapeng Liu, Youjian Zhao, Haowen Xu, Yongqian Sun, Dan Pei, Jiao Luo, Xiaowei Jing, and Mei Feng. 2015. Opprentice: Towards Practical and Automatic Anomaly Detection Through Machine Learning. In ACM IMC 2015. 211–224.
[24]
Pankaj Malhotra, Anusha Ramakrishnan, Gaurangi Anand, Lovekesh Vig, Puneet Agarwal, and Gautam Shroff. 2016. LSTM-based Encoder-Decoder for Multi-sensor Anomaly Detection. In ICML 2016 Anomaly Detection Workshop.
[25]
Guansong Pang, Chunhua Shen, Longbing Cao, and Anton van den Hengel. 2020. Deep Learning for Anomaly Detection: A Review. arxiv:2007.02500
[26]
Spiros Papadimitriou, Jimeng Sun, and Philip S. Yu. 2006. Local Correlation Tracking in Time Series. In IEEE ICDM 2006. 456–465.
[27]
Shaogang Ren, Dingcheng Li, Zhixin Zhou, and Ping Li. 2020. Estimate the Implicit Likelihoods of GANs with Application to Anomaly Detection. In WWW ’20: The Web Conference 2020. 2287–2297.
[28]
Danilo Jimenez Rezende, Shakir Mohamed, and Daan Wierstra. 2014. Stochastic Backpropagation and Approximate Inference in Deep Generative Models. In ICML 2014. 1278–1286.
[29]
Taeshik Shon and Jongsub Moon. 2007. A hybrid machine learning approach to network anomaly detection. Inf. Sci. 177, 18 (2007), 3799–3821.
[30]
Dongjin Song, Ning Xia, Wei Cheng, Haifeng Chen, and Dacheng Tao. 2018. Deep r -th Root of Rank Supervised Joint Binary Embedding for Multivariate Time Series Retrieval. In ACM SIGKDD 2018. 2229–2238.
[31]
Ya Su, Youjian Zhao, Chenhao Niu, Rong Liu, Wei Sun, and Dan Pei. 2019. Robust Anomaly Detection for Multivariate Time Series through Stochastic Recurrent Neural Network. In ACM SIGKDD 2019. 2828–2837.
[32]
Ilya Sutskever, Oriol Vinyals, and Quoc V. Le. 2014. Sequence to Sequence Learning with Neural Networks. In NIPS 2014. 3104–3112.
[33]
Laurens van der Maaten. 2014. Accelerating t-SNE using tree-based algorithms. J. Mach. Learn. Res. 15, 1 (2014), 3221–3245.
[34]
Ruben Villegas, Jimei Yang, Seunghoon Hong, Xunyu Lin, and Honglak Lee. 2017. Decomposing Motion and Content for Natural Video Sequence Prediction. In ICLR 2017.
[35]
Haowen Xu, Wenxiao Chen, Nengwen Zhao, Zeyan Li, Jiahao Bu, Zhihan Li, Ying Liu, Youjian Zhao, Dan Pei, Yang Feng, Jie Chen, Zhaogang Wang, and Honglin Qiao. 2018. Unsupervised Anomaly Detection via Variational Auto-Encoder for Seasonal KPIs in Web Applications. In WWW 2018. 187–196.
[36]
Li Xu, Jimmy S. J. Ren, Ce Liu, and Jiaya Jia. 2014. Deep Convolutional Neural Network for Image Deconvolution. In NIPS 2014. 1790–1798.
[37]
Makoto Yamada, Akisato Kimura, Futoshi Naya, and Hiroshi Sawada. 2013. Change-Point Detection with Feature Selection in High-Dimensional Time-Series Data. In IJCAI 2013. 1827–1833.
[38]
Chiyuan Zhang, Samy Bengio, Moritz Hardt, Benjamin Recht, and Oriol Vinyals. 2017. Understanding deep learning requires rethinking generalization. In ICLR 2017.
[39]
Chuxu Zhang, Dongjin Song, Yuncong Chen, Xinyang Feng, Cristian Lumezanu, Wei Cheng, Jingchao Ni, Bo Zong, Haifeng Chen, and Nitesh V. Chawla. 2019. A Deep Neural Network for Unsupervised Anomaly Detection and Diagnosis in Multivariate Time Series Data. In AAAI 2019. 1409–1416.
[40]
Stephan Zheng, Yang Song, Thomas Leung, and Ian J. Goodfellow. 2016. Improving the Robustness of Deep Neural Networks via Stability Training. In IEEE CVPR 2016. 4480–4488.
[41]
Chong Zhou and Randy C. Paffenroth. 2017. Anomaly Detection with Robust Deep Autoencoders. In ACM SIGKDD 2017. 665–674.
[42]
Bo Zong, Qi Song, Martin Renqiang Min, Wei Cheng, Cristian Lumezanu, Dae-ki Cho, and Haifeng Chen. 2018. Deep Autoencoding Gaussian Mixture Model for Unsupervised Anomaly Detection. In ICLR 2018.

Cited By

View all
  • (2024)Interpretable Failure Localization for Microservice Systems Based on Graph AutoencoderACM Transactions on Software Engineering and Methodology10.1145/369599934:2(1-28)Online publication date: 13-Sep-2024
  • (2024)Revisiting VAE for Unsupervised Time Series Anomaly Detection: A Frequency PerspectiveProceedings of the ACM Web Conference 202410.1145/3589334.3645710(3096-3105)Online publication date: 13-May-2024
  • (2024)Multivariate Time Series Anomaly Detection based on Pre-trained Models with Dual-Attention Mechanism2024 IEEE 35th International Symposium on Software Reliability Engineering Workshops (ISSREW)10.1109/ISSREW63542.2024.00050(73-78)Online publication date: 28-Oct-2024
  • Show More Cited By

Recommendations

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences
WWW '21: Proceedings of the Web Conference 2021
April 2021
4054 pages
ISBN:9781450383127
DOI:10.1145/3442381
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Sponsors

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 03 June 2021

Permissions

Request permissions for this article.

Check for updates

Author Tags

  1. Content Delivery Network
  2. Latent Variable Model
  3. Multivariate Anomaly Detection
  4. Static and Dynamic Factorization

Qualifiers

  • Research-article
  • Research
  • Refereed limited

Conference

WWW '21
Sponsor:
WWW '21: The Web Conference 2021
April 19 - 23, 2021
Ljubljana, Slovenia

Acceptance Rates

Overall Acceptance Rate 1,899 of 8,196 submissions, 23%

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • Downloads (Last 12 months)103
  • Downloads (Last 6 weeks)10
Reflects downloads up to 19 Feb 2025

Other Metrics

Citations

Cited By

View all
  • (2024)Interpretable Failure Localization for Microservice Systems Based on Graph AutoencoderACM Transactions on Software Engineering and Methodology10.1145/369599934:2(1-28)Online publication date: 13-Sep-2024
  • (2024)Revisiting VAE for Unsupervised Time Series Anomaly Detection: A Frequency PerspectiveProceedings of the ACM Web Conference 202410.1145/3589334.3645710(3096-3105)Online publication date: 13-May-2024
  • (2024)Multivariate Time Series Anomaly Detection based on Pre-trained Models with Dual-Attention Mechanism2024 IEEE 35th International Symposium on Software Reliability Engineering Workshops (ISSREW)10.1109/ISSREW63542.2024.00050(73-78)Online publication date: 28-Oct-2024
  • (2023)Stacked adversarial variational recurrent neural network for anomaly detection of multivariate time seriesSCIENTIA SINICA Informationis10.1360/SSI-2022-0277Online publication date: 11-Sep-2023
  • (2023)IAD-Net: Multivariate KPIs Interpretable Anomaly Detection with Dual Gated Residual Fusion Networks2023 IEEE 22nd International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)10.1109/TrustCom60117.2023.00103(686-693)Online publication date: 1-Nov-2023
  • (2023)Robust Failure Diagnosis of Microservice System Through Multimodal DataIEEE Transactions on Services Computing10.1109/TSC.2023.329001816:6(3851-3864)Online publication date: Nov-2023
  • (2023)A Multivariate KPIs Anomaly Detection Framework With Dynamic Balancing Loss TrainingIEEE Transactions on Network and Service Management10.1109/TNSM.2022.322480320:2(1418-1429)Online publication date: 1-Jun-2023
  • (2023)Efficient and Robust KPI Outlier Detection for Large-Scale DatacentersIEEE Transactions on Computers10.1109/TC.2023.327228872:10(2858-2871)Online publication date: 1-Oct-2023
  • (2023)ADTCD: An Adaptive Anomaly Detection Approach Toward Concept Drift in IoTIEEE Internet of Things Journal10.1109/JIOT.2023.326596410:18(15931-15942)Online publication date: 15-Sep-2023
  • (2023)fKPISelect: Fault-Injection Based Automated KPI Selection for Practical Multivariate Anomaly Detection2023 IEEE 34th International Symposium on Software Reliability Engineering (ISSRE)10.1109/ISSRE59848.2023.00084(183-194)Online publication date: 9-Oct-2023
  • Show More Cited By

View Options

Login options

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

HTML Format

View this article in HTML Format.

HTML Format

Figures

Tables

Media

Share

Share

Share this Publication link

Share on social media