DeepGate: Global-local decomposition for multivariate time series modeling
•A global–local decomposition is introduced for interpretable time series modeling.•A time series model that sustains the global–local decomposition is proposed.•The denoising training method is applied to make the forecasting model robust.•The proposed method outperforms the baselines on several da...
Saved in:
Published in | Information sciences Vol. 590; pp. 158 - 178 |
---|---|
Main Authors | , , , |
Format | Journal Article |
Language | English |
Published |
Elsevier Inc
01.04.2022
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | •A global–local decomposition is introduced for interpretable time series modeling.•A time series model that sustains the global–local decomposition is proposed.•The denoising training method is applied to make the forecasting model robust.•The proposed method outperforms the baselines on several datasets for forecasting.•Explicit decomposition empowers the model to disentangle underlying shared effects.
In multivariate time series, a substantial amount of variables exhibit common dynamics stemming from a small number of global factors. Recent studies have shown that the shared information from global components can enhance the forecasting performance of time series. However, existing global–local approaches treat the global factors as additional hidden states inside the model without providing global series for downstream analysis. In this study, we propose DeepGate, a novel time series forecasting framework based on the explicit global–local decomposition. To retain the global and local series property, we have built decomposition and prediction modules separately. In this way, DeepGate can produce interpretable global series for further tasks while improving forecasting performance with the aid of global and local series. In addition, to alleviate the discrepancy between the training and testing steps, we employ a denoising training technique for multi-step forecasting problems. In numerous experiments on real-world benchmarks for time series forecasting, DeepGate outperforms the baselines including existing global–local models. In particular, the experimental results on synthetic tasks demonstrate that our model can effectively extract underlying global series. |
---|---|
AbstractList | •A global–local decomposition is introduced for interpretable time series modeling.•A time series model that sustains the global–local decomposition is proposed.•The denoising training method is applied to make the forecasting model robust.•The proposed method outperforms the baselines on several datasets for forecasting.•Explicit decomposition empowers the model to disentangle underlying shared effects.
In multivariate time series, a substantial amount of variables exhibit common dynamics stemming from a small number of global factors. Recent studies have shown that the shared information from global components can enhance the forecasting performance of time series. However, existing global–local approaches treat the global factors as additional hidden states inside the model without providing global series for downstream analysis. In this study, we propose DeepGate, a novel time series forecasting framework based on the explicit global–local decomposition. To retain the global and local series property, we have built decomposition and prediction modules separately. In this way, DeepGate can produce interpretable global series for further tasks while improving forecasting performance with the aid of global and local series. In addition, to alleviate the discrepancy between the training and testing steps, we employ a denoising training technique for multi-step forecasting problems. In numerous experiments on real-world benchmarks for time series forecasting, DeepGate outperforms the baselines including existing global–local models. In particular, the experimental results on synthetic tasks demonstrate that our model can effectively extract underlying global series. |
Author | Park, Chanhee Choi, Jonghwan Park, Jinuk Park, Sanghyun |
Author_xml | – sequence: 1 givenname: Jinuk surname: Park fullname: Park, Jinuk – sequence: 2 givenname: Chanhee surname: Park fullname: Park, Chanhee – sequence: 3 givenname: Jonghwan surname: Choi fullname: Choi, Jonghwan – sequence: 4 givenname: Sanghyun surname: Park fullname: Park, Sanghyun email: sanghyun@yonsei.ac.kr |
BookMark | eNp9kMFKAzEQhoNUsK0-gLe8wK6T7Ca71ZNUW5WCFz2HbDIrKdlNSdaCb29KPQs_zGW-4Z9vQWZjGJGQWwYlAybv9qUbU8mB8xJYjrggc9Y2vJB8xWZkDsChAC7EFVmktAeAupFyTt6eEA9bPeE93frQaV_4YLSnFk0YDiG5yYWR9iHS4dtP7qijy8t0cgPShNFhokOw6N34dU0ue-0T3vzNJfncPH-sX4rd-_Z1_bgrDOfNVBjbSSOtNUaiqIVtODeAFmpoa6x1_qbBvuqgbYWwtmYsN9fVquqZbDuoRLUk7HzXxJBSxF4doht0_FEM1EmG2qssQ51kKGA5J-bhzGAudnQYVTIOR4PWRTSTssH9Q_8CVT9poQ |
CitedBy_id | crossref_primary_10_1007_s10489_023_04987_6 crossref_primary_10_1016_j_ins_2023_119410 crossref_primary_10_3390_su151411123 crossref_primary_10_1016_j_ins_2023_119560 crossref_primary_10_1016_j_ins_2022_12_099 |
Cites_doi | 10.1198/jasa.2011.tm09771 10.1162/neco.1997.9.8.1735 10.24963/ijcai.2018/505 10.1109/TETCI.2021.3100641 10.3354/cr030079 10.1093/oxfordhb/9780195398649.013.0003 10.1016/j.neucom.2020.03.011 10.1038/s41598-020-65070-5 10.1080/00031305.2017.1380080 10.1016/bs.hesmac.2016.04.002 10.24963/ijcai.2017/366 10.3141/1748-12 10.1016/j.ijforecast.2019.07.001 10.1016/S0925-2312(03)00372-2 10.12785/amis/080617 |
ContentType | Journal Article |
Copyright | 2022 Elsevier Inc. |
Copyright_xml | – notice: 2022 Elsevier Inc. |
DBID | AAYXX CITATION |
DOI | 10.1016/j.ins.2022.01.015 |
DatabaseName | CrossRef |
DatabaseTitle | CrossRef |
DatabaseTitleList | |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Engineering Library & Information Science |
EISSN | 1872-6291 |
EndPage | 178 |
ExternalDocumentID | 10_1016_j_ins_2022_01_015 S0020025522000184 |
GroupedDBID | --K --M --Z -~X .DC .~1 0R~ 1B1 1OL 1RT 1~. 1~5 29I 4.4 457 4G. 5GY 5VS 7-5 71M 8P~ 9JN 9JO AAAKF AAAKG AABNK AACTN AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AARIN AAXUO AAYFN ABAOU ABBOA ABEFU ABFNM ABJNI ABMAC ABTAH ABUCO ABXDB ABYKQ ACAZW ACDAQ ACGFS ACNNM ACRLP ACZNC ADBBV ADEZE ADGUI ADJOM ADMUD ADTZH AEBSH AECPX AEKER AENEX AFFNX AFKWA AFTJW AGHFR AGUBO AGYEJ AHHHB AHJVU AHZHX AIALX AIEXJ AIGVJ AIKHN AITUG AJBFU AJOXV ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD APLSM ARUGR ASPBG AVWKF AXJTR AZFZN BJAXD BKOJK BLXMC CS3 DU5 EBS EFJIC EFLBG EJD EO8 EO9 EP2 EP3 F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN G-Q GBLVA GBOLZ HAMUX HLZ HVGLF HZ~ H~9 IHE J1W JJJVA KOM LG9 LY1 M41 MHUIS MO0 MS~ N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 R2- RIG ROL RPZ SBC SDF SDG SDP SDS SES SEW SPC SPCBC SSB SSD SST SSV SSW SSZ T5K TN5 TWZ UHS WH7 WUQ XPP YYP ZMT ZY4 ~02 ~G- AAXKI AAYXX ADVLN AFJKZ AKRWK CITATION |
ID | FETCH-LOGICAL-c227t-cdb6c6ddcc6e545d722c0ed04084e4a1017ef3b08855dd411020a393f168b0353 |
IEDL.DBID | AIKHN |
ISSN | 0020-0255 |
IngestDate | Thu Sep 26 15:52:40 EDT 2024 Fri Feb 23 02:43:10 EST 2024 |
IsPeerReviewed | true |
IsScholarly | true |
Keywords | Interpretable neural networks Multivariate time series Time series analysis Global-local decomposition Multi-step forecasting |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-c227t-cdb6c6ddcc6e545d722c0ed04084e4a1017ef3b08855dd411020a393f168b0353 |
PageCount | 21 |
ParticipantIDs | crossref_primary_10_1016_j_ins_2022_01_015 elsevier_sciencedirect_doi_10_1016_j_ins_2022_01_015 |
PublicationCentury | 2000 |
PublicationDate | April 2022 2022-04-00 |
PublicationDateYYYYMMDD | 2022-04-01 |
PublicationDate_xml | – month: 04 year: 2022 text: April 2022 |
PublicationDecade | 2020 |
PublicationTitle | Information sciences |
PublicationYear | 2022 |
Publisher | Elsevier Inc |
Publisher_xml | – name: Elsevier Inc |
References | Lv, Duan, Kang, Li, Wang (b0025) 2015; 16 Sen, Yu, Dhillon (b0045) 2019 Bengio, Vinyals, Jaitly, Shazeer (b0150) 2015 Wu, Lobato, Ghahramani (b0015) 2013 Franceschi, Dieuleveut, Jaggi (b0115) 2019 Chen, Kang, Chen, Wang (b0120) 2020; 399 J. Chung, C. Gulcehre, K. Cho, Y. Bengio, Empirical evaluation of gated recurrent neural networks on sequence modeling, (2014). Raffel, Shazeer, Roberts, Lee, Narang, Matena, Zhou, Li, Liu (b0165) 2020; 21 Simchi-Levi, Kaminsky (b0080) 2001; 22 Y. Qin, D. Song, H. Cheng, W. Cheng, G. Jiang, G.W. Cottrell, A dual-stage attention-based recurrent neural network for time series prediction, in: IJCAI International Joint Conference on Artificial Intelligence, 2017. Lai, Chang, Yang, Liu (b0125) 2018 Ranzato, Chopra, Auli, Zaremba (b0155) 2016 O. Ogunmolu, X. Gu, S. Jiang, N. Gans, Nonlinear Systems Identification Using Deep Dynamic Neural Networks, 2016, arXiv preprint arXiv:1610.01439. Yan, Mu, Wang, Ranjan, Zomaya (b0110) 2020; 10 Ma, Zheng, Li, Cottrell (b0210) 2021; 32 B. Yu, H. Yin, Z. Zhu, Spatio-temporal graph convolutional networks: A deep learning framework for traffic forecasting, in: IJCAI International Joint Conference on Artificial Intelligence, 2018. Pang, Yao, Zhou, Zhang, Xu, Tan (b0020) 2018 Cleveland, Cleveland, McRae, Terpenning (b0035) 1990; 6 J.H. Stock, M.W. Watson, Dynamic factor models, Oxford Handbooks Online, 2011. Geweke (b0075) 1977 Cuturi (b0190) 2011 Stock, Watson (b0140) 2016 Box, Jenkins, Reinsel, Ljung (b0030) 2015 S. Bai, J.Z. Kolter, V. Koltun, An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling, 2018, arXiv preprint arXiv:1803.0127. Kim (b0010) 2003; 55 De Livera, Hyndman, Snyder (b0185) 2011; 106 Chen, Petty, Skabardonis, Varaiya, Jia (b0195) 2001; 1748 Abo-Hammour, Abu Arqub, Alsmadi, Momani, Alsaedi (b0205) 2014; 8 Yu, Rao, Dhillon (b0050) 2016 Taylor, Letham (b0180) 2018; 72 Wang, Smola, Maddix, Gasthaus, Foster, Januschowski (b0060) 2019 R.J. Hyndman, G. Athanasopoulos, Forecasting: principles and practice, OTexts, 2018. Seeger, Salinas, Flunkert (b0005) 2016 (b0085) 2005 A. van den Oord, S. Dieleman, H. Zen, K. Simonyan, O. Vinyals, A. Graves, N. Kalchbrenner, A. Senior, K. Kavukcuoglu, WaveNet: A Generative Model for Raw Audio Based on PixelCNN Architecture, 2016, arXiv preprint arXiv:1609.03499. Salinas, Flunkert, Gasthaus, Januschowski (b0055) 2020; 36 Hochreiter, Schmidhuber (b0095) 1997; 9 Dagum, Bianconcini (b0135) 2016 Li, Jin, Xuan, Zhou, Chen, Wang, Yan (b0175) 2019 Lewis, Liu, Goyal, Ghazvininejad, Mohamed, Levy, Stoyanov, Zettlemoyer, Bart (b0160) 2020 Willmott, Matsuura (b0170) 2005; 30 Zhang, Tino, Leonardis, Tang (b0145) 2021; 5 10.1016/j.ins.2022.01.015_b0105 Zhang (10.1016/j.ins.2022.01.015_b0145) 2021; 5 Lv (10.1016/j.ins.2022.01.015_b0025) 2015; 16 Sen (10.1016/j.ins.2022.01.015_b0045) 2019 Li (10.1016/j.ins.2022.01.015_b0175) 2019 Chen (10.1016/j.ins.2022.01.015_b0195) 2001; 1748 Simchi-Levi (10.1016/j.ins.2022.01.015_b0080) 2001; 22 Franceschi (10.1016/j.ins.2022.01.015_b0115) 2019 Lewis (10.1016/j.ins.2022.01.015_b0160) 2020 Chen (10.1016/j.ins.2022.01.015_b0120) 2020; 399 Cuturi (10.1016/j.ins.2022.01.015_b0190) 2011 10.1016/j.ins.2022.01.015_b0090 Ma (10.1016/j.ins.2022.01.015_b0210) 2021; 32 Yu (10.1016/j.ins.2022.01.015_b0050) 2016 10.1016/j.ins.2022.01.015_b0070 Ranzato (10.1016/j.ins.2022.01.015_b0155) 2016 Raffel (10.1016/j.ins.2022.01.015_b0165) 2020; 21 Taylor (10.1016/j.ins.2022.01.015_b0180) 2018; 72 Seeger (10.1016/j.ins.2022.01.015_b0005) 2016 (10.1016/j.ins.2022.01.015_b0085) 2005 Yan (10.1016/j.ins.2022.01.015_b0110) 2020; 10 10.1016/j.ins.2022.01.015_b0130 Kim (10.1016/j.ins.2022.01.015_b0010) 2003; 55 Wu (10.1016/j.ins.2022.01.015_b0015) 2013 Lai (10.1016/j.ins.2022.01.015_b0125) 2018 Pang (10.1016/j.ins.2022.01.015_b0020) 2018 De Livera (10.1016/j.ins.2022.01.015_b0185) 2011; 106 Cleveland (10.1016/j.ins.2022.01.015_b0035) 1990; 6 Salinas (10.1016/j.ins.2022.01.015_b0055) 2020; 36 Dagum (10.1016/j.ins.2022.01.015_b0135) 2016 Stock (10.1016/j.ins.2022.01.015_b0140) 2016 Hochreiter (10.1016/j.ins.2022.01.015_b0095) 1997; 9 Box (10.1016/j.ins.2022.01.015_b0030) 2015 10.1016/j.ins.2022.01.015_b0040 Wang (10.1016/j.ins.2022.01.015_b0060) 2019 Willmott (10.1016/j.ins.2022.01.015_b0170) 2005; 30 Geweke (10.1016/j.ins.2022.01.015_b0075) 1977 10.1016/j.ins.2022.01.015_b0065 Abo-Hammour (10.1016/j.ins.2022.01.015_b0205) 2014; 8 10.1016/j.ins.2022.01.015_b0100 Bengio (10.1016/j.ins.2022.01.015_b0150) 2015 10.1016/j.ins.2022.01.015_b0200 |
References_xml | – year: 2016 ident: b0050 article-title: Temporal regularized matrix factorization for high-dimensional time series prediction publication-title: Advances in Neural Information Processing Systems contributor: fullname: Dhillon – year: 2019 ident: b0175 article-title: Enhancing the locality and breaking the memory bottleneck of transformer on time series forecasting publication-title: Advances in Neural Information Processing Systems contributor: fullname: Yan – volume: 72 start-page: 37 year: 2018 end-page: 45 ident: b0180 article-title: Forecasting at Scale publication-title: American Statistician contributor: fullname: Letham – volume: 36 start-page: 1181 year: 2020 end-page: 1191 ident: b0055 article-title: DeepAR: Probabilistic forecasting with autoregressive recurrent networks publication-title: International Journal of Forecasting contributor: fullname: Januschowski – volume: 399 start-page: 491 year: 2020 end-page: 501 ident: b0120 article-title: Probabilistic forecasting with temporal convolutional neural network publication-title: Neurocomputing contributor: fullname: Wang – year: 2019 ident: b0060 article-title: Deep factors for forecasting publication-title: 36th International Conference on Machine Learning, ICML 2019 contributor: fullname: Januschowski – year: 2005 ident: b0085 publication-title: New Introduction to Multiple Time Series Analysis – volume: 21 year: 2020 ident: b0165 article-title: Exploring the limits of transfer learning with a unified text-to-text transformer publication-title: Journal of Machine Learning Research contributor: fullname: Liu – volume: 10 year: 2020 ident: b0110 article-title: Temporal Convolutional Networks for the Advance Prediction of ENSO publication-title: Scientific Reports contributor: fullname: Zomaya – year: 2015 ident: b0030 article-title: Time series analysis: forecasting and control contributor: fullname: Ljung – year: 2018 ident: b0020 article-title: Hierarchical electricity time series forecasting for integrating consumption patterns analysis and aggregation consistency publication-title: IJCAI International Joint Conference on Artificial Intelligence contributor: fullname: Tan – year: 2016 ident: b0005 article-title: Bayesian intermittent demand forecasting for large inventories publication-title: Advances in Neural Information Processing Systems contributor: fullname: Flunkert – volume: 8 start-page: 2809 year: 2014 end-page: 2821 ident: b0205 article-title: An optimization algorithm for solving systems of singular boundary value problems publication-title: Applied Mathematics and Information Sciences contributor: fullname: Alsaedi – volume: 22 year: 2001 ident: b0080 article-title: Designing and Managing the Supply Chain: Concepts, Strategies, and Case Studies publication-title: Journal of Business Logistics contributor: fullname: Kaminsky – year: 2018 ident: b0125 article-title: Modeling long- and short-term temporal patterns with deep neural networks publication-title: 41st International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2018 contributor: fullname: Liu – volume: 1748 start-page: 96 year: 2001 end-page: 102 ident: b0195 article-title: Freeway performance measurement system: mining loop detector data publication-title: Transportation Research Record contributor: fullname: Jia – volume: 6 year: 1990 ident: b0035 article-title: STL: A Seasonal-Trend Decomposition Procedure Based on Loess (with Discussion) publication-title: Journal of Official Statistics contributor: fullname: Terpenning – year: 2013 ident: b0015 article-title: Dynamic covariance models for multivariate financial time series publication-title: 30th International Conference on Machine Learning, ICML 2013 contributor: fullname: Ghahramani – volume: 106 start-page: 1513 year: 2011 end-page: 1527 ident: b0185 article-title: Forecasting time series with complex seasonal patterns using exponential smoothing publication-title: Journal of the American Statistical Association contributor: fullname: Snyder – year: 2015 ident: b0150 article-title: Scheduled sampling for sequence prediction with recurrent neural networks publication-title: Advances in Neural Information Processing Systems contributor: fullname: Shazeer – volume: 5 start-page: 726 year: 2021 end-page: 742 ident: b0145 article-title: A Survey on Neural Network Interpretability publication-title: IEEE Transactions on Emerging Topics in Computational Intelligence contributor: fullname: Tang – year: 2016 ident: b0155 article-title: Sequence level training with recurrent neural networks publication-title: 4th International Conference on Learning Representations, ICLR 2016 - Conference Track Proceedings contributor: fullname: Zaremba – year: 2016 ident: b0135 article-title: Seasonal adjustment methods and real time trend-cycle estimation contributor: fullname: Bianconcini – volume: 32 year: 2021 ident: b0210 article-title: Learning Representations for Incomplete Time Series Clustering publication-title: AAAI contributor: fullname: Cottrell – volume: 16 year: 2015 ident: b0025 article-title: Traffic Flow Prediction with Big Data: A Deep Learning Approach publication-title: IEEE Transactions on Intelligent Transportation Systems contributor: fullname: Wang – year: 2011 ident: b0190 article-title: Fast global alignment kernels publication-title: Proceedings of the 28th International Conference on Machine Learning, ICML 2011 contributor: fullname: Cuturi – volume: 55 start-page: 307 year: 2003 end-page: 319 ident: b0010 article-title: Financial time series forecasting using support vector machines publication-title: Neurocomputing contributor: fullname: Kim – year: 2020 ident: b0160 article-title: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation publication-title: Translation, and Comprehension, in contributor: fullname: Bart – volume: 30 start-page: 79 year: 2005 end-page: 82 ident: b0170 article-title: Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance publication-title: Climate Research contributor: fullname: Matsuura – year: 2019 ident: b0115 article-title: Unsupervised scalable representation learning for multivariate time series publication-title: Advances in Neural Information Processing Systems contributor: fullname: Jaggi – volume: 9 start-page: 1735 year: 1997 end-page: 1780 ident: b0095 article-title: Long Short-Term Memory publication-title: Neural Computation contributor: fullname: Schmidhuber – year: 2016 ident: b0140 article-title: Dynamic Factor Models, Factor-Augmented Vector Autoregressions, and Structural Vector Autoregressions in Macroeconomics publication-title: Handbook of Macroeconomics contributor: fullname: Watson – year: 2019 ident: b0045 article-title: Think globally, act locally: A deep neural network approach to high-dimensional time series forecasting publication-title: Advances in Neural Information Processing Systems contributor: fullname: Dhillon – year: 1977 ident: b0075 article-title: The dynamic factor analysis of economic time-series models publication-title: Latent Variable in Socioeconomic Models contributor: fullname: Geweke – volume: 106 start-page: 1513 issue: 496 year: 2011 ident: 10.1016/j.ins.2022.01.015_b0185 article-title: Forecasting time series with complex seasonal patterns using exponential smoothing publication-title: Journal of the American Statistical Association doi: 10.1198/jasa.2011.tm09771 contributor: fullname: De Livera – year: 2015 ident: 10.1016/j.ins.2022.01.015_b0150 article-title: Scheduled sampling for sequence prediction with recurrent neural networks contributor: fullname: Bengio – volume: 22 year: 2001 ident: 10.1016/j.ins.2022.01.015_b0080 article-title: Designing and Managing the Supply Chain: Concepts, Strategies, and Case Studies publication-title: Journal of Business Logistics contributor: fullname: Simchi-Levi – volume: 9 start-page: 1735 issue: 8 year: 1997 ident: 10.1016/j.ins.2022.01.015_b0095 article-title: Long Short-Term Memory publication-title: Neural Computation doi: 10.1162/neco.1997.9.8.1735 contributor: fullname: Hochreiter – ident: 10.1016/j.ins.2022.01.015_b0200 doi: 10.24963/ijcai.2018/505 – volume: 5 start-page: 726 issue: 5 year: 2021 ident: 10.1016/j.ins.2022.01.015_b0145 article-title: A Survey on Neural Network Interpretability publication-title: IEEE Transactions on Emerging Topics in Computational Intelligence doi: 10.1109/TETCI.2021.3100641 contributor: fullname: Zhang – year: 2019 ident: 10.1016/j.ins.2022.01.015_b0115 article-title: Unsupervised scalable representation learning for multivariate time series contributor: fullname: Franceschi – year: 2019 ident: 10.1016/j.ins.2022.01.015_b0045 article-title: Think globally, act locally: A deep neural network approach to high-dimensional time series forecasting contributor: fullname: Sen – volume: 30 start-page: 79 year: 2005 ident: 10.1016/j.ins.2022.01.015_b0170 article-title: Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance publication-title: Climate Research doi: 10.3354/cr030079 contributor: fullname: Willmott – ident: 10.1016/j.ins.2022.01.015_b0070 doi: 10.1093/oxfordhb/9780195398649.013.0003 – volume: 21 year: 2020 ident: 10.1016/j.ins.2022.01.015_b0165 article-title: Exploring the limits of transfer learning with a unified text-to-text transformer publication-title: Journal of Machine Learning Research contributor: fullname: Raffel – year: 2013 ident: 10.1016/j.ins.2022.01.015_b0015 article-title: Dynamic covariance models for multivariate financial time series contributor: fullname: Wu – year: 2019 ident: 10.1016/j.ins.2022.01.015_b0060 article-title: Deep factors for forecasting contributor: fullname: Wang – volume: 399 start-page: 491 year: 2020 ident: 10.1016/j.ins.2022.01.015_b0120 article-title: Probabilistic forecasting with temporal convolutional neural network publication-title: Neurocomputing doi: 10.1016/j.neucom.2020.03.011 contributor: fullname: Chen – volume: 10 issue: 1 year: 2020 ident: 10.1016/j.ins.2022.01.015_b0110 article-title: Temporal Convolutional Networks for the Advance Prediction of ENSO publication-title: Scientific Reports doi: 10.1038/s41598-020-65070-5 contributor: fullname: Yan – ident: 10.1016/j.ins.2022.01.015_b0090 – volume: 72 start-page: 37 issue: 1 year: 2018 ident: 10.1016/j.ins.2022.01.015_b0180 article-title: Forecasting at Scale publication-title: American Statistician doi: 10.1080/00031305.2017.1380080 contributor: fullname: Taylor – year: 2018 ident: 10.1016/j.ins.2022.01.015_b0125 article-title: Modeling long- and short-term temporal patterns with deep neural networks contributor: fullname: Lai – year: 2005 ident: 10.1016/j.ins.2022.01.015_b0085 – year: 2016 ident: 10.1016/j.ins.2022.01.015_b0005 article-title: Bayesian intermittent demand forecasting for large inventories contributor: fullname: Seeger – ident: 10.1016/j.ins.2022.01.015_b0100 – year: 2015 ident: 10.1016/j.ins.2022.01.015_b0030 contributor: fullname: Box – volume: 16 year: 2015 ident: 10.1016/j.ins.2022.01.015_b0025 article-title: Traffic Flow Prediction with Big Data: A Deep Learning Approach publication-title: IEEE Transactions on Intelligent Transportation Systems contributor: fullname: Lv – year: 2019 ident: 10.1016/j.ins.2022.01.015_b0175 article-title: Enhancing the locality and breaking the memory bottleneck of transformer on time series forecasting contributor: fullname: Li – year: 2016 ident: 10.1016/j.ins.2022.01.015_b0140 article-title: Dynamic Factor Models, Factor-Augmented Vector Autoregressions, and Structural Vector Autoregressions in Macroeconomics doi: 10.1016/bs.hesmac.2016.04.002 contributor: fullname: Stock – ident: 10.1016/j.ins.2022.01.015_b0105 doi: 10.24963/ijcai.2017/366 – ident: 10.1016/j.ins.2022.01.015_b0130 – year: 2020 ident: 10.1016/j.ins.2022.01.015_b0160 article-title: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation publication-title: Translation, and Comprehension, in contributor: fullname: Lewis – year: 2016 ident: 10.1016/j.ins.2022.01.015_b0050 article-title: Temporal regularized matrix factorization for high-dimensional time series prediction contributor: fullname: Yu – volume: 1748 start-page: 96 issue: 1 year: 2001 ident: 10.1016/j.ins.2022.01.015_b0195 article-title: Freeway performance measurement system: mining loop detector data publication-title: Transportation Research Record doi: 10.3141/1748-12 contributor: fullname: Chen – year: 1977 ident: 10.1016/j.ins.2022.01.015_b0075 article-title: The dynamic factor analysis of economic time-series models contributor: fullname: Geweke – year: 2011 ident: 10.1016/j.ins.2022.01.015_b0190 article-title: Fast global alignment kernels contributor: fullname: Cuturi – ident: 10.1016/j.ins.2022.01.015_b0040 – ident: 10.1016/j.ins.2022.01.015_b0065 – volume: 36 start-page: 1181 year: 2020 ident: 10.1016/j.ins.2022.01.015_b0055 article-title: DeepAR: Probabilistic forecasting with autoregressive recurrent networks publication-title: International Journal of Forecasting doi: 10.1016/j.ijforecast.2019.07.001 contributor: fullname: Salinas – year: 2016 ident: 10.1016/j.ins.2022.01.015_b0155 article-title: Sequence level training with recurrent neural networks contributor: fullname: Ranzato – year: 2018 ident: 10.1016/j.ins.2022.01.015_b0020 article-title: Hierarchical electricity time series forecasting for integrating consumption patterns analysis and aggregation consistency contributor: fullname: Pang – volume: 6 year: 1990 ident: 10.1016/j.ins.2022.01.015_b0035 article-title: STL: A Seasonal-Trend Decomposition Procedure Based on Loess (with Discussion) publication-title: Journal of Official Statistics contributor: fullname: Cleveland – volume: 55 start-page: 307 issue: 1-2 year: 2003 ident: 10.1016/j.ins.2022.01.015_b0010 article-title: Financial time series forecasting using support vector machines publication-title: Neurocomputing doi: 10.1016/S0925-2312(03)00372-2 contributor: fullname: Kim – volume: 8 start-page: 2809 issue: 6 year: 2014 ident: 10.1016/j.ins.2022.01.015_b0205 article-title: An optimization algorithm for solving systems of singular boundary value problems publication-title: Applied Mathematics and Information Sciences doi: 10.12785/amis/080617 contributor: fullname: Abo-Hammour – year: 2016 ident: 10.1016/j.ins.2022.01.015_b0135 contributor: fullname: Dagum – volume: 32 year: 2021 ident: 10.1016/j.ins.2022.01.015_b0210 article-title: Learning Representations for Incomplete Time Series Clustering publication-title: AAAI contributor: fullname: Ma |
SSID | ssj0004766 |
Score | 2.4525137 |
Snippet | •A global–local decomposition is introduced for interpretable time series modeling.•A time series model that sustains the global–local decomposition is... |
SourceID | crossref elsevier |
SourceType | Aggregation Database Publisher |
StartPage | 158 |
SubjectTerms | Global-local decomposition Interpretable neural networks Multi-step forecasting Multivariate time series Time series analysis |
Title | DeepGate: Global-local decomposition for multivariate time series modeling |
URI | https://dx.doi.org/10.1016/j.ins.2022.01.015 |
Volume | 590 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV07T8MwED71scCAoIAo0MoDYkAyTRw7D7aqUJUidaJSt6h-RCpDqEph5LdzdhxRJFiQsuRxSnSx72F_3x3AVbgMi7QICprhbYoeT9A0MzFNtA4LYRjGyK7a5yyezPl0IRYNGNVcGAur9La_sunOWvsrA6_NwXq1shxf5iJiZtkmmKg0oY3uiPMWtIePT5PZNz0yqbYsbaZkBerNTQfzWpW2aDdjrninbY77m3vacTnjQzjwsSIZVp9zBA1TdmB_p4JgB3qed0CuiScWWUUTP2OPYXpvzNqukN2Rqro_dc6LaGOx5B6wRVCQOGThB2bO-DCxHeeJHZzmjbheOfiyE5iPH55HE-rbJ1DFWLKlSstYxVorFRuMk3TCmAqMxlmbcsOXdi6aIpJoZoTQmmMcwIJllEVFGKcyiER0Cq3ytTRnQBSXQhZGSi0xlU4xG49VkCnJdZhiSsS6cFNrLV9XVTLyGj72kqOKc6viPAjxEF3gtV7zH786Ryv-t9j5_8QuYM-eVWCbS2htN--mh3HEVvahefsZ9v1o-QKnwsc3 |
link.rule.ids | 315,786,790,4521,24144,27955,27956,45618,45712 |
linkProvider | Elsevier |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV07T8MwED6VMgADggKiPD0gBqTQxInzYEOFqpTSqZW6RfUjUhlCBYWR386d44giwYKUKfYp0cW--y7-7g7gIpgFRVr4hZfhsIceT3hpZmIv0ToohOGIkW21z1Hcn0SDqZg2oFvnwhCt0tn-yqZba-3udJw2O4v5nHJ8uUXEnLJNMFBZg3VCA8Truv785nlESXVgSXESTa-PNi3Ja15SyW7ObelOao37m3NacTi9Hdh2SJHdVi-zCw1TtmBrpX5gC05d1gG7ZC6tiNTM3H7dg8GdMQv6P3bDqtr-nnVdTBtikju6FkNBZnmFHxg342RG_eYZLU3zxmynHHzYPkx69-Nu33PNEzzFebL0lJaxirVWKjaIknTCufKNxj2bRiaa0U40RSjRyAihdYQogPuzMAuLIE6lH4rwAJrlS2kOgalIClkYKbXEQDrFWDxWfqZkpIMUAyLehqtaa_miqpGR1-Sx5xxVnJOKcz_AS7QhqvWa__jQOdrwv8WO_id2Dhv98dMwHz6MHo9hk0Yq2s0JNJev7-YUEcVSntkV8wVnaMgM |
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%3Ajournal&rft.genre=article&rft.atitle=DeepGate%3A+Global-local+decomposition+for+multivariate+time+series+modeling&rft.jtitle=Information+sciences&rft.au=Park%2C+Jinuk&rft.au=Park%2C+Chanhee&rft.au=Choi%2C+Jonghwan&rft.au=Park%2C+Sanghyun&rft.date=2022-04-01&rft.issn=0020-0255&rft.volume=590&rft.spage=158&rft.epage=178&rft_id=info:doi/10.1016%2Fj.ins.2022.01.015&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_ins_2022_01_015 |
thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0020-0255&client=summon |
thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0020-0255&client=summon |
thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0020-0255&client=summon |