{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T21:17:18Z","timestamp":1783027038191,"version":"3.54.6"},"reference-count":42,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62372466"],"award-info":[{"award-number":["62372466"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62476022"],"award-info":[{"award-number":["62476022"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Natural Science Foundation of Beijing Municipality","doi-asserted-by":"publisher","award":["4254085"],"award-info":[{"award-number":["4254085"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Natural Science Foundation of Beijing Municipality","doi-asserted-by":"publisher","award":["L242047"],"award-info":[{"award-number":["L242047"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Natural Science Foundation of Beijing Municipality","doi-asserted-by":"publisher","award":["L251043"],"award-info":[{"award-number":["L251043"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2024YFF0505704"],"award-info":[{"award-number":["2024YFF0505704"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005090","name":"Beijing Nova Program","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100005090","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.patcog.2026.113996","type":"journal-article","created":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T15:13:43Z","timestamp":1780586023000},"page":"113996","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PB","title":["Multi-level decoupled trend learning for GNN-based multivariate time series prediction"],"prefix":"10.1016","volume":"180","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-8609-7876","authenticated-orcid":false,"given":"Shaohan","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7315-3276","authenticated-orcid":false,"given":"Zhenfeng","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9326-9863","authenticated-orcid":false,"given":"Youru","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6288-453X","authenticated-orcid":false,"given":"Yeyu","family":"Yan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuai","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7608-3112","authenticated-orcid":false,"given":"Pengyuan","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Zhuang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yao","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.113996_b1","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109670","article-title":"A decomposition dynamic graph convolutional recurrent network for traffic forecasting","volume":"142","author":"Weng","year":"2023","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113996_b2","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2019.05.028","article-title":"EA-LSTM: Evolutionary attention-based LSTM for time series prediction","volume":"181","author":"Li","year":"2019","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.patcog.2026.113996_b3","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110985","article-title":"Dynamic convolutional time series forecasting based on adaptive temporal bilateral filtering","volume":"158","author":"Zhang","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113996_b4","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.111037","article-title":"Parallel multi-scale dynamic graph neural network for multivariate time series forecasting","volume":"158","author":"Hou","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113996_b5","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.110075","article-title":"Time pattern reconstruction for classification of irregularly sampled time series","volume":"147","author":"Sun","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113996_b6","first-page":"15715","article-title":"Fully-connected spatial-temporal graph for multivariate time-series data","volume":"vol. 38, no. 14","author":"Wang","year":"2024"},{"key":"10.1016\/j.patcog.2026.113996_b7","doi-asserted-by":"crossref","unstructured":"B. Yu, H. Yin, Z. Zhu, Spatio-temporal graph convolutional networks: a deep learning framework for traffic forecasting, in: Proc. IJCAI, 2018, pp. 3634\u20133640.","DOI":"10.24963\/ijcai.2018\/505"},{"key":"10.1016\/j.patcog.2026.113996_b8","unstructured":"Y. Li, R. Yu, C. Shahabi, Y. Liu, Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting, in: Proc. ICLR, 2018."},{"key":"10.1016\/j.patcog.2026.113996_b9","doi-asserted-by":"crossref","unstructured":"X. Rao, H. Wang, L. Zhang, J. Li, S. Shang, P. Han, FOGS: First-Order Gradient Supervision with Learning-based Graph for Traffic Flow Forecasting, in: Proc. IJCAI, 2022, pp. 3926\u20133932.","DOI":"10.24963\/ijcai.2022\/545"},{"key":"10.1016\/j.patcog.2026.113996_b10","unstructured":"H. Lee, S. Ko, TESTAM: A Time-Enhanced Spatio-Temporal Attention Model with Mixture of Experts, in: Proc. ICLR, 2024."},{"issue":"6","key":"10.1016\/j.patcog.2026.113996_b11","doi-asserted-by":"crossref","first-page":"1359","DOI":"10.1109\/TVCG.2009.200","article-title":"Visualization and exploration of temporal trend relationships in multivariate time-varying data","volume":"15","author":"Lee","year":"2009","journal-title":"IEEE Trans. Vis. Comput. Graphics"},{"key":"10.1016\/j.patcog.2026.113996_b12","doi-asserted-by":"crossref","first-page":"118","DOI":"10.1016\/j.fss.2015.05.011","article-title":"Description of multivariate time series by means of trends characterization in the fuzzy domain","volume":"285","author":"Moreno-Garcia","year":"2016","journal-title":"Fuzzy Sets and Systems"},{"issue":"38","key":"10.1016\/j.patcog.2026.113996_b13","doi-asserted-by":"crossref","first-page":"14889","DOI":"10.1073\/pnas.0701020104","article-title":"On the trend, detrending, and variability of nonlinear and nonstationary time series","volume":"104","author":"Wu","year":"2007","journal-title":"Proc. Natl. Acad. Sci."},{"issue":"4","key":"10.1016\/j.patcog.2026.113996_b14","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1086\/647609","article-title":"An introduction to time-trend analysis","volume":"18","author":"Birnbaum","year":"1997","journal-title":"Infect. Control Hosp. Epidemiol."},{"key":"10.1016\/j.patcog.2026.113996_b15","series-title":"Time Series Analysis: Forecasting and Control","author":"Box","year":"2015"},{"issue":"1","key":"10.1016\/j.patcog.2026.113996_b16","first-page":"136","article-title":"Integrating granger causality and vector auto-regression for traffic prediction of large-scale WLANs","volume":"10","author":"Lu","year":"2016","journal-title":"KSII T. Internet Inf."},{"key":"10.1016\/j.patcog.2026.113996_b17","first-page":"11141","article-title":"Msgnet: Learning multi-scale inter-series correlations for multivariate time series forecasting","volume":"vol. 38, no. 10","author":"Cai","year":"2024"},{"key":"10.1016\/j.patcog.2026.113996_b18","unstructured":"H. Gao, R. Jiang, Z. Dong, J. Deng, Y. Ma, X. Song, Spatial-Temporal-Decoupled Masked Pre-training for Spatiotemporal Forecasting, in: Proc. IJCAI, 2024, pp. 3998\u20134006."},{"key":"10.1016\/j.patcog.2026.113996_b19","first-page":"4365","article-title":"Pdformer: Propagation delay-aware dynamic long-range transformer for traffic flow prediction","volume":"vol. 37, no. 4","author":"Jiang","year":"2023"},{"issue":"10","key":"10.1016\/j.patcog.2026.113996_b20","doi-asserted-by":"crossref","first-page":"10748","DOI":"10.1109\/TKDE.2023.3268199","article-title":"Multi-scale adaptive graph neural network for multivariate time series forecasting","volume":"35","author":"Chen","year":"2023","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"10.1016\/j.patcog.2026.113996_b21","doi-asserted-by":"crossref","unstructured":"Z. Dong, R. Jiang, H. Gao, H. Liu, J. Deng, Q. Wen, X. Song, Heterogeneity-informed meta-parameter learning for spatiotemporal time series forecasting, in: Proc. SIGKDD, 2024, pp. 631\u2013641.","DOI":"10.1145\/3637528.3671961"},{"key":"10.1016\/j.patcog.2026.113996_b22","doi-asserted-by":"crossref","first-page":"1421","DOI":"10.1007\/s10994-019-05815-0","article-title":"Temporal pattern attention for multivariate time series forecasting","volume":"108","author":"Shih","year":"2019","journal-title":"Mach. Learn."},{"key":"10.1016\/j.patcog.2026.113996_b23","doi-asserted-by":"crossref","unstructured":"G. Lai, W.-C. Chang, Y. Yang, H. Liu, Modeling long-and short-term temporal patterns with deep neural networks, in: Proc. SIGIR, 2018, pp. 95\u2013104.","DOI":"10.1145\/3209978.3210006"},{"key":"10.1016\/j.patcog.2026.113996_b24","first-page":"11106","article-title":"Informer: Beyond efficient transformer for long sequence time-series forecasting","volume":"vol. 35, no. 12","author":"Zhou","year":"2021"},{"key":"10.1016\/j.patcog.2026.113996_b25","first-page":"22419","article-title":"Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting","volume":"vol. 34","author":"Wu","year":"2021"},{"issue":"1","key":"10.1016\/j.patcog.2026.113996_b26","doi-asserted-by":"crossref","first-page":"141","DOI":"10.26599\/TST.2021.9010081","article-title":"Multivariate time series forecasting with transfer entropy graph","volume":"28","author":"Duan","year":"2022","journal-title":"Tsinghua Sci. Technol."},{"key":"10.1016\/j.patcog.2026.113996_b27","doi-asserted-by":"crossref","unstructured":"Z. Wu, S. Pan, G. Long, J. Jiang, C. Zhang, Graph wavenet for deep spatial-temporal graph modeling, in: Proc. IJCAI, 2019, pp. 1907\u20131913.","DOI":"10.24963\/ijcai.2019\/264"},{"key":"10.1016\/j.patcog.2026.113996_b28","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1016\/j.patrec.2021.12.008","article-title":"MTHetGNN: A heterogeneous graph embedding framework for multivariate time series forecasting","volume":"153","author":"Wang","year":"2022","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113996_b29","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.112586","article-title":"Dynamic multi-scale spatial-temporal graph convolutional network for traffic flow prediction","volume":"305","author":"Gao","year":"2024","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.patcog.2026.113996_b30","unstructured":"S. Wang, H. Wu, X. Shi, T. Hu, H. Luo, L. Ma, J.Y. Zhang, J. Zhou, TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting, in: Proc. ICLR, 2024."},{"key":"10.1016\/j.patcog.2026.113996_b31","first-page":"12694","article-title":"Chattime: A unified multimodal time series foundation model bridging numerical and textual data","volume":"vol. 39, no. 12","author":"Wang","year":"2025"},{"key":"10.1016\/j.patcog.2026.113996_b32","first-page":"18915","article-title":"Calf: Aligning llms for time series forecasting via cross-modal fine-tuning","volume":"vol. 39, no. 18","author":"Liu","year":"2025"},{"key":"10.1016\/j.patcog.2026.113996_b33","unstructured":"A. Vaswani, Attention is all you need, in: Proc. NeurIPS, 2017."},{"key":"10.1016\/j.patcog.2026.113996_b34","first-page":"9089","article-title":"Towards dynamic spatial-temporal graph learning: A decoupled perspective","volume":"vol. 38, no. 8","author":"Wang","year":"2024"},{"issue":"2","key":"10.1016\/j.patcog.2026.113996_b35","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3589270","article-title":"Lightcts: A lightweight framework for correlated time series forecasting","volume":"1","author":"Lai","year":"2023","journal-title":"Proc. ACM Manag. Data"},{"key":"10.1016\/j.patcog.2026.113996_b36","first-page":"914","article-title":"Spatial-temporal synchronous graph convolutional networks: A new framework for spatial-temporal network data forecasting","volume":"vol. 34, no. 01","author":"Song","year":"2020"},{"key":"10.1016\/j.patcog.2026.113996_b37","doi-asserted-by":"crossref","unstructured":"Y. Zheng, X. Yi, M. Li, R. Li, Z. Shan, E. Chang, T. Li, Forecasting fine-grained air quality based on big data, in: Proc. SIGKDD, 2015, pp. 2267\u20132276.","DOI":"10.1145\/2783258.2788573"},{"key":"10.1016\/j.patcog.2026.113996_b38","unstructured":"A. Cini, D. Mandic, C. Alippi, Graph-based Time Series Clustering for End-to-End Hierarchical Forecasting, in: Proc. ICML, 2024, pp. 8985\u20138999."},{"key":"10.1016\/j.patcog.2026.113996_b39","series-title":"Breakthroughs in Statistics: Methodology and Distribution","first-page":"492","article-title":"Robust estimation of a location parameter","author":"Huber","year":"1992"},{"key":"10.1016\/j.patcog.2026.113996_b40","first-page":"11121","article-title":"Are transformers effective for time series forecasting?","volume":"vol. 37, no. 9","author":"Zeng","year":"2023"},{"key":"10.1016\/j.patcog.2026.113996_b41","doi-asserted-by":"crossref","unstructured":"Z. Wu, S. Pan, G. Long, J. Jiang, X. Chang, C. Zhang, Connecting the dots: Multivariate time series forecasting with graph neural networks, in: Proc. SIGKDD, 2020, pp. 753\u2013763.","DOI":"10.1145\/3394486.3403118"},{"key":"10.1016\/j.patcog.2026.113996_b42","unstructured":"C. Shang, J. Chen, Discrete Graph Structure Learning for Forecasting Multiple Time Series, in: Proc. ICLR, 2021."}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326009611?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326009611?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T20:25:57Z","timestamp":1783023957000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326009611"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":42,"alternative-id":["S0031320326009611"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113996","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Multi-level decoupled trend learning for GNN-based multivariate time series prediction","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113996","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"113996"}}