{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T18:03:41Z","timestamp":1778609021467,"version":"3.51.4"},"reference-count":208,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001711","name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","doi-asserted-by":"publisher","award":["204061"],"award-info":[{"award-number":["204061"]}],"id":[{"id":"10.13039\/501100001711","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["FT210100097"],"award-info":[{"award-number":["FT210100097"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["DP240101547"],"award-info":[{"award-number":["DP240101547"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tpami.2024.3443141","type":"journal-article","created":{"date-parts":[[2024,8,14]],"date-time":"2024-08-14T17:35:31Z","timestamp":1723656931000},"page":"10466-10485","source":"Crossref","is-referenced-by-count":362,"title":["A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detection"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6833-4811","authenticated-orcid":false,"given":"Ming","family":"Jin","sequence":"first","affiliation":[{"name":"School of Information and Communication Technology, Griffith University, Nathan, QLD, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0488-2616","authenticated-orcid":false,"given":"Huan Yee","family":"Koh","sequence":"additional","affiliation":[{"name":"Department of Data Science and AI, Monash University, Clayton, VIC, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4516-2524","authenticated-orcid":false,"given":"Qingsong","family":"Wen","sequence":"additional","affiliation":[{"name":"Squirrel AI Learning, Bellevue, WA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3722-9784","authenticated-orcid":false,"given":"Daniele","family":"Zambon","sequence":"additional","affiliation":[{"name":"Swiss AI Lab IDSIA, Università della Svizzera Italiana, Lugano, Switzerland"}]},{"given":"Cesare","family":"Alippi","sequence":"additional","affiliation":[{"name":"Swiss AI Lab IDSIA, Università della Svizzera Italiana, Lugano, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9963-5169","authenticated-orcid":false,"given":"Geoffrey I.","family":"Webb","sequence":"additional","affiliation":[{"name":"Department of Data Science and AI, Monash University, Clayton, VIC, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8106-6447","authenticated-orcid":false,"given":"Irwin","family":"King","sequence":"additional","affiliation":[{"name":"Department of Computer Science & Engineering, Chinese University of Hong Kong, Ma Liu Shui, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0794-527X","authenticated-orcid":false,"given":"Shirui","family":"Pan","sequence":"additional","affiliation":[{"name":"School of Information and Communication Technology, Griffith University, Nathan, QLD, Australia"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3542612"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/2379776.2379788"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3387317"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.2020.0209"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-019-00619-1"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3444690"},{"key":"ref7","article-title":"Time series data imputation: A survey on deep learning approaches","author":"Fang","year":"2020"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2011.2158001"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2022.3175252"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2958185"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.3025580"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3043250"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.117921"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-021-02587-w"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/tkde.2023.3333824"},{"key":"ref16","article-title":"Spatio-temporal graph neural networks: A survey","author":"Sahili","year":"2023"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3257759"},{"key":"ref18","article-title":"Taming local effects in graph-based spatiotemporal forecasting","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Cini"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2003.820556"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.2991\/fmsmt-17.2017.87"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/937332.937333"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1970.10481180"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3221989"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21629\/JSEE.2017.01.18"},{"key":"ref25","article-title":"Conditional time series forecasting with convolutional neural networks","author":"Borovykh","year":"2017"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/72.279188"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/759"},{"key":"ref28","article-title":"How expressive are spectral-temporal graph neural networks for time series forecasting?","author":"Jin","year":"2023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978386"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467422"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3232398"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-024-00847-1"},{"key":"ref33","article-title":"Graph-guided network for irregularly sampled multivariate time series","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2023.3239797"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM50108.2020.00093"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i5.16523"},{"key":"ref37","article-title":"Filling the G_ap_s: Multivariate time series imputation by graph neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Cini"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE55515.2023.00150"},{"key":"ref39","article-title":"Neural temporal walks: Motif-aware representation learning on continuous-time dynamic graphs","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Jin"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3172903"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013656"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380097"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207457"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i5.16542"},{"key":"ref45","first-page":"3374","article-title":"Sparse Granger causality graphs for human action classification","volume-title":"Proc. Int. Conf. Pattern Recognit.","author":"Yi"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2021.12.008"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2927301"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/264"},{"key":"ref49","article-title":"Adaptive graph convolutional recurrent network for traffic forecasting","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Bai"},{"key":"ref50","article-title":"Spectral temporal graph neural network for multivariate time-series forecasting","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Cao"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403118"},{"key":"ref52","article-title":"Discrete graph structure learning for forecasting multiple time series","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Shang"},{"issue":"242","key":"ref53","first-page":"1","article-title":"Sparse graph learning from spatiotemporal time series","volume":"24","author":"Cini","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/505"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3589132.3625614"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539117"},{"key":"ref57","article-title":"Graph-augmented normalizing flows for anomaly detection of multiple time series","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dai"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2804443"},{"key":"ref59","article-title":"Where and how to improve graph-based spatio-temporal predictors","author":"Zambon","year":"2023"},{"key":"ref60","article-title":"Multivariate time-series forecasting with temporal polynomial graph neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539396"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3325667"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611977172.23"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2024.120914"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86362-3_20"},{"key":"ref66","article-title":"Spatial aggregation and temporal convolution networks for real-time Kriging","author":"Wu","year":"2021"},{"key":"ref67","article-title":"Learning to reconstruct missing data from spatiotemporal graphs with sparse observations","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Marisca"},{"key":"ref68","article-title":"Diffusion convolutional recurrent neural network: Data-driven traffic forecasting","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5758"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5477"},{"key":"ref71","first-page":"1684","article-title":"Z-GCNETs: Time zigzags at graph convolutional networks for time series forecasting","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/328"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i5.16575"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467430"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i6.20587"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330884"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i6.25880"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1145\/3437963.3441827"},{"key":"ref79","first-page":"3621","article-title":"Deep variational graph convolutional recurrent network for multivariate time series anomaly detection","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3167640"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2022.103826"},{"key":"ref82","article-title":"Multivariate time series anomaly detection via dynamic graph forecasting","author":"Chen","year":"2023"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_30"},{"key":"ref84","article-title":"Event2Graph: Event-driven bipartite graph for multivariate time-series anomaly detection","author":"Wu","year":"2021"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3171780"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301922"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380186"},{"key":"ref88","first-page":"11 906","article-title":"DSTAGNN: Dynamic spatial-temporal aware graph neural network for traffic flow forecasting","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lan"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3100509"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/332"},{"key":"ref91","article-title":"Deciphering spatio-temporal graph forecasting: A causal lens and treatment","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Xia"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5438"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.14778\/3489496.3489503"},{"key":"ref94","first-page":"1","article-title":"Graph attention recurrent neural networks for correlated time series forecasting","volume-title":"Proc. 5th SIGKDD Workshop Mining Learn. Time Ser.","author":"Cirstea"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5470"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3094908"},{"key":"ref97","article-title":"LB-SimTSC: An efficient similarity-aware graph neural network for semi-supervised time series classification","author":"Xi","year":"2023"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2235192"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2013.2238935"},{"key":"ref100","first-page":"28 877","article-title":"Do transformers really perform badly for graph representation?","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ying"},{"key":"ref101","first-page":"3408","article-title":"On the connection between MPNN and graph transformer","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Cai"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.3390\/electronics8080876"},{"key":"ref103","first-page":"7052","article-title":"On the equivalence between temporal and static equivariant graph representations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gao"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2019.8852131"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/326"},{"key":"ref106","article-title":"Graph edit networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Paassen"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539394"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/545"},{"key":"ref109","article-title":"Graph-based time series clustering for end-to-end hierarchical forecasting","author":"Cini","year":"2023"},{"key":"ref110","article-title":"GPT-ST: Generative pre-training of spatio-temporal graph neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210006"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-019-05815-0"},{"key":"ref113","first-page":"3837","article-title":"Convolutional neural networks on graphs with fast localized spectral filtering","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Defferrard"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.113"},{"key":"ref115","first-page":"1263","article-title":"Neural message passing for quantum chemistry","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gilmer"},{"key":"ref116","first-page":"13 333","article-title":"Diffusion improves graph learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Klicpera"},{"key":"ref117","article-title":"Finding the missing-half: Graph complementary learning for homophily-prone and heterophily-prone graphs","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zheng"},{"key":"ref118","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","volume-title":"Proc. NeurIPS Workshop Deep Learn.","author":"Chung"},{"key":"ref119","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kipf"},{"key":"ref120","article-title":"Graph attention networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Velickovic"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013558"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557540"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1145\/3571285"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3411940"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301890"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i1.16088"},{"key":"ref128","first-page":"6572","article-title":"Neural ordinary differential equations","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref129","article-title":"Neural controlled differential equations for irregular time series","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Kidger"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.3390\/e24060759"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1109\/BigData55660.2022.10020888"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9892295"},{"key":"ref133","article-title":"Time series subsequence anomaly detection via graph neural networks","author":"Chen","year":"2023"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-015-3994-4"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2013.12.026"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1145\/3691338"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2005.79"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3120277"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2801475"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219845"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330672"},{"key":"ref142","article-title":"Anomaly transformer: Time series anomaly detection with association discrepancy","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xu"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482057"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3119326"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3105827"},{"key":"ref146","volume-title":"Deep Learning","author":"Goodfellow","year":"2016"},{"key":"ref147","first-page":"1185","article-title":"Sparse feature learning for deep belief networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ranzato"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1561\/2200000056"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2019.2953596"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102255"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2022.07.032"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2023.109614"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110486"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1145\/3649448"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-014-0361-2"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109333"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1145\/3182382"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-06057-9"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-020-00701-z"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-022-00844-1"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5769"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.14778\/3407790.3407792"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-004-0154-9"},{"key":"ref164","article-title":"Self-supervised graph neural networks for improved electroencephalographic seizure analysis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Tang"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1109\/ICDMW58026.2022.00101"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-1642-9_6"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.110188"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.02.017"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583525"},{"key":"ref170","article-title":"Imputation as inpainting: Diffusion models for spatiotemporal data imputation","author":"Yun","year":"2023"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.32614\/rj-2017-009"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1109\/SMC42975.2020.9283191"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-018-24271-9"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i10.17086"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557294"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1145\/3564753"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.1049\/itr2.12265"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3103502"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.3390\/s20226433"},{"key":"ref180","doi-asserted-by":"publisher","DOI":"10.1016\/j.renene.2022.09.036"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.1049\/rpg2.12449"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2021.3133289"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1109\/TIA.2022.3213008"},{"key":"ref184","doi-asserted-by":"publisher","DOI":"10.3390\/atmos14020308"},{"key":"ref185","article-title":"Forecasting global weather with graph neural networks","author":"Keisler","year":"2022"},{"key":"ref186","first-page":"4502","article-title":"Interaction networks for learning about objects, relations and physics","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Battaglia"},{"key":"ref187","article-title":"Towards complex dynamic physics system simulation with graph neural ODEs","author":"Shi","year":"2023"},{"key":"ref188","first-page":"21867","article-title":"Graph switching dynamical systems","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu"},{"key":"ref189","article-title":"Equivariant spatio-temporal attentive graph networks to simulate physical dynamics","volume-title":"Proc. 37th Int. Conf. Neural Inf. Process. Syst.","author":"Wu"},{"key":"ref190","article-title":"Hamiltonian graph networks with ODE integrators","author":"Sanchez-Gonzalez","year":"2019"},{"key":"ref191","article-title":"SEGNO: Generalizing equivariant graph neural networks with physical inductive biases","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu"},{"key":"ref192","first-page":"9323","article-title":"E(n) equivariant graph neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Satorras"},{"key":"ref193","article-title":"Geometric and physical quantities improve E(3) equivariant message passing","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Brandstetter"},{"key":"ref194","doi-asserted-by":"publisher","DOI":"10.6339\/22-JDS1047"},{"key":"ref195","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3615091"},{"key":"ref196","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403364"},{"key":"ref197","doi-asserted-by":"publisher","DOI":"10.1016\/j.est.2022.106437"},{"key":"ref198","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301346"},{"key":"ref199","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC57777.2023.10422572"},{"key":"ref200","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i6.16616"},{"key":"ref201","article-title":"Large models for time series and spatio-temporal data: A survey and outlook","author":"Jin","year":"2023"},{"key":"ref202","article-title":"A survey of large language models","author":"Zhao","year":"2023"},{"key":"ref203","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2024.3369017"},{"key":"ref204","doi-asserted-by":"publisher","DOI":"10.1145\/3565973"},{"key":"ref205","doi-asserted-by":"publisher","DOI":"10.1145\/3468218.3469046"},{"key":"ref206","first-page":"1024","article-title":"Inductive representation learning on large graphs","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Hamilton"},{"key":"ref207","article-title":"FastGCN: Fast learning with graph convolutional networks via importance sampling","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen"},{"key":"ref208","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330925"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/34\/10746266\/10636792-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10746266\/10636792.pdf?arnumber=10636792","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:26:36Z","timestamp":1732667196000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10636792\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":208,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3443141","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}