{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T12:27:00Z","timestamp":1777984020916,"version":"3.51.4"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Knowl. Data Eng."],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1109\/tkde.2026.3679682","type":"journal-article","created":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T19:53:39Z","timestamp":1774986819000},"page":"3792-3805","source":"Crossref","is-referenced-by-count":0,"title":["ODGNet: Learning Dynamic Variable Association for Online Time Series Forecasting"],"prefix":"10.1109","volume":"38","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-2557-1952","authenticated-orcid":false,"given":"Yushuo","family":"Liu","sequence":"first","affiliation":[{"name":"College of Computer Science, Nankai University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8425-6045","authenticated-orcid":false,"given":"Yulong","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Computer Science, Nankai University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5589-7060","authenticated-orcid":false,"given":"Kai","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Computer Science, Nankai University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE55515.2023.00081"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3322405"},{"key":"ref3","first-page":"2216","article-title":"Full Bayesian significance testing for neural networks in traffic forecasting","volume-title":"Proc. 33rd Int. Joint Conf. Artif. Intell.","author":"Liu"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2023.3333921"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2024.3468433"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2024.3488783"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00667-9"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3060"},{"issue":"2","key":"ref9","article-title":"The problem of concept drift: Definitions and related work","volume":"106","author":"Tsymbal","year":"2004","journal-title":"Comput. Sci. Dept., Trinity College Dublin"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2018.2876857"},{"key":"ref11","first-page":"17766","article-title":"Spectral temporal graph neural network for multivariate time-series forecasting","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Cao"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17325"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/264"},{"key":"ref14","article-title":"Learning fast and slow for online time series forecasting","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Pham","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.14778\/3551793.3551827"},{"key":"ref16","first-page":"19414","article-title":"Multivariate time-series forecasting with temporal polynomial graph neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.14778\/3636218.3636230"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0766"},{"key":"ref19","first-page":"928","article-title":"Online convex programming and generalized infinitesimal gradient ascent","volume-title":"Proc. 20th Int. Conf. Mach. Learn.","author":"Zinkevich"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.04.112"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1057\/9781137291264_6"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.2307\/1912017"},{"key":"ref23","first-page":"54509","article-title":"Sparse deep learning for time series data: Theory and applications","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i1.27768"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671969"},{"key":"ref26","article-title":"A time series is worth 64 words: Long-term forecasting with transformers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Nie","year":"2023"},{"key":"ref27","article-title":"CrossFormer: Transformer utilizing cross-dimension dependency for multivariate time series forecasting","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang","year":"2023"},{"key":"ref28","article-title":"iTransformer: Inverted transformers are effective for time series forecasting","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu","year":"2024"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3333824"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3268199"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3383895"},{"key":"ref32","first-page":"3998","article-title":"Spatial-temporal-decoupled masked pre-training for spatiotemporal forecasting","volume-title":"Proc. 33rd Int. Joint Conf. Artif. Intell.","author":"Gao"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3066"},{"key":"ref34","first-page":"1190","article-title":"Time series prediction and online learning","volume-title":"Proc. Conf. Learn. Theory","author":"Kuznetsov"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i15.33717"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5984"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3336191.3371845"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2024.3489420"},{"key":"ref39","article-title":"On tiny episodic memories in continual learning","author":"Chaudhry","year":"2019"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3484454"},{"key":"ref41","first-page":"26227","article-title":"TimeBase: The power of minimalism in efficient long-term time series forecasting","volume-title":"Proc. 42nd Int. Conf. Mach. Learn.","author":"Huang"},{"key":"ref42","first-page":"22419","article-title":"AutoFormer: Decomposition transformers with auto-correlation for long-term series forecasting","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wu"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210006"},{"key":"ref44","first-page":"5816","article-title":"SCINet: Time series modeling and forecasting with sample convolution and interaction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref45","article-title":"Diffusion convolutional recurrent neural network: Data-driven traffic forecasting","author":"Li","year":"2017"},{"key":"ref46","first-page":"15920","article-title":"Dark experience for general continual learning: A strong, simple baseline","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Buzzega"},{"key":"ref47","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov"}],"container-title":["IEEE Transactions on Knowledge and Data Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/69\/11503382\/11459376.pdf?arnumber=11459376","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T05:03:05Z","timestamp":1777698185000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11459376\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":47,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tkde.2026.3679682","relation":{"has-preprint":[{"id-type":"doi","id":"10.36227\/techrxiv.174286313.38634064\/v1","asserted-by":"object"}]},"ISSN":["1041-4347","1558-2191","2326-3865"],"issn-type":[{"value":"1041-4347","type":"print"},{"value":"1558-2191","type":"electronic"},{"value":"2326-3865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6]]}}}