seq2graph: Discovering Dynamic Non-linear Dependencies from Multivariate Time Series

Discovering temporal lagged and inter-dependencies in multivariate time series data is an important task. However, in many real-world applications with big data, such as commercial cloud management or predictive maintenance in manufacturing, such dependencies can be time-variant and non-linear, whic...

Full description

Saved in:
Bibliographic Details
Published in:2019 IEEE International Conference on Big Data (Big Data) pp. 1774 - 1783
Main Authors: Dang, Xuan-Hong, Shah, Syed Yousaf, Zerfos, Petros
Format: Conference Proceeding
Language:English
Published: IEEE 01.12.2019
Subjects:
Big Data
Data models
Logic gates
Multivariate Time Series
Neural Network
Predictive models
Recurrent neural networks
Task analysis
Time series analysis
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Discovering temporal lagged and inter-dependencies in multivariate time series data is an important task. However, in many real-world applications with big data, such as commercial cloud management or predictive maintenance in manufacturing, such dependencies can be time-variant and non-linear, which makes it more challenging to extract such dependencies through traditional methods like Granger causality or statistical models. In this work, we present a novel deep learning model that uses multiple layers of adapted gated recurrent units (GRUs) for discovering both time lagged behaviors and inter-timeseries dependencies, representing them in the form of directed weighted graphs. Each individual time series is first analyzed by a pair of encoding-decoding GRUs in order to discover the time lagged dependencies and representing its samples as high dimensional vectors. Such vectors collected from all component time series are then analyzed by a decoding network component to discover inter-dependencies across all time series while forecasting their next values in the multivariate time series. Though the discovery of two types of dependencies are separated at two levels of our neural network, they are tightly connected and jointly trained in an end-to-end manner. With this joint training, improvement in learning of one type of dependency immediately impacts the learning process of the other one, leading to the overall highly accurate dependencies discovery. We empirically test our model on synthetic time series data in which the exact form of dependencies are known. We also practically evaluate its performance on two real-world applications, (i) dynamic multivariate performance monitoring data with high volatility from a commercial cloud provider and, (ii) multivariate time series generated by sensors for a manufacturing plant. We show how our approach is capable of capturing these dependency behaviors via intuitive and interpretable dependency graphs and use them to generate forecasting values.
AbstractList Discovering temporal lagged and inter-dependencies in multivariate time series data is an important task. However, in many real-world applications with big data, such as commercial cloud management or predictive maintenance in manufacturing, such dependencies can be time-variant and non-linear, which makes it more challenging to extract such dependencies through traditional methods like Granger causality or statistical models. In this work, we present a novel deep learning model that uses multiple layers of adapted gated recurrent units (GRUs) for discovering both time lagged behaviors and inter-timeseries dependencies, representing them in the form of directed weighted graphs. Each individual time series is first analyzed by a pair of encoding-decoding GRUs in order to discover the time lagged dependencies and representing its samples as high dimensional vectors. Such vectors collected from all component time series are then analyzed by a decoding network component to discover inter-dependencies across all time series while forecasting their next values in the multivariate time series. Though the discovery of two types of dependencies are separated at two levels of our neural network, they are tightly connected and jointly trained in an end-to-end manner. With this joint training, improvement in learning of one type of dependency immediately impacts the learning process of the other one, leading to the overall highly accurate dependencies discovery. We empirically test our model on synthetic time series data in which the exact form of dependencies are known. We also practically evaluate its performance on two real-world applications, (i) dynamic multivariate performance monitoring data with high volatility from a commercial cloud provider and, (ii) multivariate time series generated by sensors for a manufacturing plant. We show how our approach is capable of capturing these dependency behaviors via intuitive and interpretable dependency graphs and use them to generate forecasting values.
Author Zerfos, Petros
Shah, Syed Yousaf
Dang, Xuan-Hong
Author_xml – sequence: 1
  givenname: Xuan-Hong
  surname: Dang
  fullname: Dang, Xuan-Hong
  organization: IBM TJ. Watson Research Center,Yorktown Heights,NY,10598
– sequence: 2
  givenname: Syed Yousaf
  surname: Shah
  fullname: Shah, Syed Yousaf
  organization: IBM TJ. Watson Research Center,Yorktown Heights,NY,10598
– sequence: 3
  givenname: Petros
  surname: Zerfos
  fullname: Zerfos, Petros
  organization: IBM TJ. Watson Research Center,Yorktown Heights,NY,10598
BookMark eNotj7FOwzAURY0EAy18AYv5gBQ_O3FiNmgoIBUYCHP17LwES4kTnFCpf08lOt3pHJ27YOdhCMTYLYgVgDB3j74tccY0F0aspACzMkJoEOqMLSCXBYgiK_Qlqyb6kW3E8fuel35yw56iDy0vDwF77_j7EJLOB8LISxop1BScp4k3cej52283-z1GjzPxyvfEP480TVfsosFuouvTLtnX5qlavyTbj-fX9cM28QDFnEiwrmhIOqvQktE6VVLoDFNjbCaPfblVVDQqtVZq2WCektRGuVpmkNcW1JLd_Hs9Ee3G6HuMh93pqPoDi3pPdQ
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/BigData47090.2019.9006103
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 1728108586
9781728108582
EndPage 1783
ExternalDocumentID 9006103
Genre orig-research
GroupedDBID 6IE
6IL
CBEJK
RIE
RIL
ID FETCH-LOGICAL-i118t-21bc8fe2cb3abe966432065a499b528587b3e8f34bb262fa74e2693cd2517db13
IEDL.DBID RIE
IngestDate Thu Jun 29 18:38:33 EDT 2023
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i118t-21bc8fe2cb3abe966432065a499b528587b3e8f34bb262fa74e2693cd2517db13
PageCount 10
ParticipantIDs ieee_primary_9006103
PublicationCentury 2000
PublicationDate 2019-Dec.
PublicationDateYYYYMMDD 2019-12-01
PublicationDate_xml – month: 12
  year: 2019
  text: 2019-Dec.
PublicationDecade 2010
PublicationTitle 2019 IEEE International Conference on Big Data (Big Data)
PublicationTitleAbbrev BigData
PublicationYear 2019
Publisher IEEE
Publisher_xml – name: IEEE
Score 1.7714133
Snippet Discovering temporal lagged and inter-dependencies in multivariate time series data is an important task. However, in many real-world applications with big...
SourceID ieee
SourceType Publisher
StartPage 1774
SubjectTerms Big Data
Data models
Logic gates
Multivariate Time Series
Neural Network
Predictive models
Recurrent neural networks
Task analysis
Time series analysis
Title seq2graph: Discovering Dynamic Non-linear Dependencies from Multivariate Time Series
URI https://ieeexplore.ieee.org/document/9006103
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PS8MwFH5MEfGksom_ieDRbG2SNYlHrcODjB0m7DaS9FV66XTt9vebtGUiePEWkkLghfK-L3nf9wDuecwkE0ZSgQap8JCAWqli6saxNZHUOcNGKPwmp1O1WOhZDx52WhhEbIrPcBiGzVt-tnKbcFU20iHhBmvPPSmTVqt1CHedbeboqfhITW2EjHQUarb0sPv-V-OUJm9Mjv-34wkMfgR4ZLZLLafQw7IP8wq_WGMw_UjSonKh-NKvkrRtKk-mq5IG0GjWJO1a2_oftyJBQUIaoe3WE2OPLUnQfZBwL4bVAN4nL_PnV9o1RaCF5wI1ZbF1KkfmLDcWPVkRnHkYYTxzsWOmxkpajirnwlqWsNxIgSzR3GXBmyyzMT-D_XJV4jkQaxBz9BhBYe5ZodGJ0i6xMpLM8EzgBfRDRJafre_FsgvG5d_TV3AUgt6WelzDfr3e4A0cuG1dVOvb5rC-ASjVmCs
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PS8MwGA1jinpS2cTfRvBotjZJm8Sj1jFxlh0m7DaS9qv00una7e83actE8OItJIRAQvjeS773PoTumE8F5VoQDhoIt5CAGCF9kgS-0Z5QGYVaKDwRcSznczXtoPutFgYA6uQzGLhm_ZefLpO1eyobKhdwnbXnTsA59Rq11h66bY0zh4_5R6QrzYWnPJe1pQbtjF-lU-rIMTr835pHqP8jwcPTbXA5Rh0oemhWwhetLaYfcJSXiUu_tKM4asrK43hZEAcb9QpHbXFbe3VL7DQkuJbabiw1tugSO-UHdi9jUPbR--h59jQmbVkEkls2UBHqm0RmQBPDtAFLVzijFkhoy11MQGUghWEgM8aNoSHNtOBAQ8WS1LmTpcZnJ6hbLAs4RdhogAwsSpCQWV6oVShVEhrhCapZyuEM9dyOLD4b54tFuxnnf3ffoP3x7G2ymLzErxfowB1Ak_hxibrVag1XaDfZVHm5uq4P7htAuJty
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=2019+IEEE+International+Conference+on+Big+Data+%28Big+Data%29&rft.atitle=seq2graph%3A+Discovering+Dynamic+Non-linear+Dependencies+from+Multivariate+Time+Series&rft.au=Dang%2C+Xuan-Hong&rft.au=Shah%2C+Syed+Yousaf&rft.au=Zerfos%2C+Petros&rft.date=2019-12-01&rft.pub=IEEE&rft.spage=1774&rft.epage=1783&rft_id=info:doi/10.1109%2FBigData47090.2019.9006103&rft.externalDocID=9006103