{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T21:41:10Z","timestamp":1780522870256,"version":"3.54.1"},"reference-count":217,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Key R&D Project of Zhejiang Province","award":["2024C01172"],"award-info":[{"award-number":["2024C01172"]}]},{"name":"National Key R&D Program of China","award":["2021YFB2012300"],"award-info":[{"award-number":["2021YFB2012300"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,10]]},"DOI":"10.1109\/tpami.2024.3387317","type":"journal-article","created":{"date-parts":[[2024,4,10]],"date-time":"2024-04-10T14:14:27Z","timestamp":1712758467000},"page":"6775-6794","source":"Crossref","is-referenced-by-count":185,"title":["Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospects"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1968-8004","authenticated-orcid":false,"given":"Kexin","family":"Zhang","sequence":"first","affiliation":[{"name":"Huzhou Institute of Zhejiang University, Huzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4516-2524","authenticated-orcid":false,"given":"Qingsong","family":"Wen","sequence":"additional","affiliation":[{"name":"Alibaba Group, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4059-8396","authenticated-orcid":false,"given":"Chaoli","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Zhejiang Normal University, Jinhua, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3424-6967","authenticated-orcid":false,"given":"Rongyao","family":"Cai","sequence":"additional","affiliation":[{"name":"College of Control Science and Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6833-4811","authenticated-orcid":false,"given":"Ming","family":"Jin","sequence":"additional","affiliation":[{"name":"Faculty of Information Technology, Monash University, Clayton, VIC, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4822-8939","authenticated-orcid":false,"given":"Yong","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Control Science and Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6519-676X","authenticated-orcid":false,"given":"James Y.","family":"Zhang","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2817-7337","authenticated-orcid":false,"given":"Yuxuan","family":"Liang","sequence":"additional","affiliation":[{"name":"INTR & DSA Thrust, Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9877-2716","authenticated-orcid":false,"given":"Guansong","family":"Pang","sequence":"additional","affiliation":[{"name":"School of Computing and Information Systems, Singapore Management University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7027-7916","authenticated-orcid":false,"given":"Dongjin","family":"Song","sequence":"additional","affiliation":[{"name":"School of Computing, University of Connecticut, Storrs, CT, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"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, Southport, Qld, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"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","first-page":"3995","article-title":"Deep convolutional neural networks on multichannel time series for human activity recognition","volume-title":"Proc. 24th Int. Conf. Artif. Intell.","author":"Yang"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2021.3087503"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5900"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220051"},{"key":"ref7","first-page":"1","article-title":"Unsupervised representation learning by predicting image rotations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gidaris"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.76"},{"key":"ref9","first-page":"766","article-title":"Discriminative unsupervised feature learning with convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dosovitskiy"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_45"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.552"},{"issue":"1","key":"ref13","first-page":"3","article-title":"STL: A seasonal-trend decomposition","volume":"6","author":"Cleveland","year":"1990","journal-title":"J. Official Stat."},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403271"},{"key":"ref15","first-page":"12677","article-title":"Film: Frequency improved legendre memory model for long-term time series forecasting","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhou"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3390\/technologies9010002"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2992393"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/170673"},{"key":"ref20","article-title":"Beyond just vision: A review on self-supervised representation learning on multimodal and temporal data","author":"Deldari","year":"2022"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3090866"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2022.100616"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3207050"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3172903"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3170559"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s11431-020-1647-3"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2021.3134634"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3031549"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3415112\/mm1"},{"key":"ref31","article-title":"Deep representation learning in speech processing: Challenges, recent advances, and future trends","author":"Latif","year":"2020"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3131584"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3390\/s23094221"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00674"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref36","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Caron"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-018-0596-4"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-019-00619-1"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.2020.0209"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2020.106181"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3091162"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3533382"},{"issue":"3","key":"ref43","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3444690","article-title":"A review on outlier\/anomaly detection in time series data","volume":"54","author":"Bl\u00e1zquez-Garc\u00eda","year":"2021","journal-title":"ACM Comput. Surv."},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2958185"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/631"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0254841"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-023-08459-3"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/759"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3559540"},{"key":"ref50","first-page":"19388","article-title":"Modeling irregular time series with continuous recurrent units","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","volume":"162","author":"Schirmer"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5440"},{"key":"ref52","first-page":"13016","article-title":"Timeseries anomaly detection using temporal hierarchical one-class network","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Shen"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-47426-3_39"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3516367"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i5.16523"},{"key":"ref56","first-page":"1","article-title":"Discrete graph structure learning for forecasting multiple time series","author":"Shang","journal-title":"Proc. Int. Conf. Learn. Representations"},{"key":"ref57","first-page":"1","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":"10.1016\/j.engappai.2022.105331"},{"key":"ref59","first-page":"37","article-title":"Autoencoders, unsupervised learning, and deep architectures","volume-title":"Proc. ICML Workshop Unsupervised Transfer Learn.","author":"Baldi"},{"key":"ref60","first-page":"10568","article-title":"Autowarp: Learning a warping distance from unlabeled time series using sequence autoencoders","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Abid"},{"key":"ref61","article-title":"TimeNet: Pre-trained deep recurrent neural network for time series classification","author":"Malhotra","year":"2017"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-019-55320-6"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467174"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/DDCLS52934.2021.9455535"},{"key":"ref65","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v35i10.17070","article-title":"Learning representations for time series clustering","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ma"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403392"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539117"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390294"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2017.2759301"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/BIBM47256.2019.8982996"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2021.12.061"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2014.08.092"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539396"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467401"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539394"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539329"},{"key":"ref78","first-page":"1","article-title":"Auto-encoding variational bayes","volume-title":"Proc. 2nd Int. Conf. Learn. Representations","author":"Kingma"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1561\/2200000056"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467075"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330672"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/332"},{"key":"ref83","first-page":"3621","article-title":"Deep variational graph convolutional recurrent network for multivariate time series anomaly detection","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref84","article-title":"Multi-time attention networks for irregularly sampled time series","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Shukla"},{"key":"ref85","first-page":"5937","article-title":"Learning from irregularly-sampled time series: A missing data perspective","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref86","first-page":"1","article-title":"Heteroscedastic temporal variational autoencoder for irregularly sampled time series","author":"Shukla","journal-title":"Proc. Int. Conf. Learn. Representations"},{"key":"ref87","first-page":"1","article-title":"Learning latent seasonal-trend representations for time series forecasting","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref88","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho"},{"key":"ref89","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dhariwal"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1145\/3626235"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/tkde.2024.3361474\/mm1"},{"key":"ref92","article-title":"Understanding diffusion models: A unified perspective","author":"Luo","year":"2022"},{"key":"ref93","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sohl-Dickstein"},{"key":"ref94","first-page":"11918","article-title":"Generative modeling by estimating gradients of the data distribution","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Song"},{"key":"ref95","first-page":"12438","article-title":"Improved techniques for training score-based generative models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Song"},{"key":"ref96","first-page":"1415","article-title":"Maximum likelihood training of score-based diffusion models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Song"},{"key":"ref97","first-page":"1","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2021","journal-title":"Proc. Int. Conf. Learn. Representations"},{"key":"ref98","first-page":"24804","article-title":"CSDI: Conditional score-based diffusion models for probabilistic time series imputation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tashiro"},{"key":"ref99","first-page":"8857","article-title":"Autoregressive denoising diffusion models for multivariate probabilistic time series forecasting","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rasul"},{"key":"ref100","first-page":"1","article-title":"Generative time series forecasting with diffusion, denoise, and disentanglement","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.14778\/3632093.3632101"},{"key":"ref102","first-page":"1","article-title":"Diffusion-based time series imputation and forecasting with structured state space models","author":"Alcaraz","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/tpwrs.2024.3449032"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1145\/3589132.3625614"},{"key":"ref105","first-page":"4650","article-title":"Unsupervised scalable representation learning for multivariate time series","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Franceschi"},{"key":"ref106","first-page":"1","article-title":"Unsupervised representation learning for time series with temporal neighborhood coding","author":"Tonekaboni","year":"2021","journal-title":"Proc. Int. Conf. Learn. Representations"},{"key":"ref107","first-page":"18661","article-title":"Supervised contrastive learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Khosla"},{"key":"ref108","first-page":"11964","article-title":"Neighborhood contrastive learning applied to online patient monitoring","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Y\u00e8che"},{"key":"ref109","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018"},{"key":"ref110","article-title":"Detecting anomalies within time series using local neural transformations","author":"Schneider","year":"2022"},{"key":"ref111","article-title":"Contrastive predictive coding for anomaly detection in multi-variate time series data","author":"Pranavan","year":"2022"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449903"},{"key":"ref113","first-page":"1","article-title":"Time series anomaly detection using skip-step contrastive predictive coding","volume-title":"Proc. NeurIPS Workshop: Self-Supervised Learn. - Theory Pract.","author":"Zhang"},{"key":"ref114","article-title":"An empirical evaluation of generic convolutional and recurrent networks for sequence modeling","author":"Bai","year":"2018"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482483"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/324"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3308189"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20881"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2021.108397"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2021.3111567"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0254841"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2022.02.007"},{"key":"ref123","first-page":"1","article-title":"CoST: Contrastive learning of disentangled seasonal-trend representations for time series forecasting","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Woo"},{"key":"ref124","first-page":"25038","article-title":"Unsupervised time-series representation learning with iterative bilinear temporal-spectral fusion","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Yang"},{"key":"ref125","first-page":"3988","article-title":"Self-supervised contrastive pre-training for time series via time-frequency consistency","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599295"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.108606"},{"key":"ref128","first-page":"5606","article-title":"CLOCS: Contrastive learning of cardiac signals across space, time, and patients","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Kiyasseh"},{"key":"ref129","first-page":"1","article-title":"Contrastive learning for unsupervised domain adaptation of time series","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ozyurt"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2022.3227960"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512056"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/537"},{"key":"ref133","first-page":"9929","article-title":"Understanding contrastive representation learning through alignment and uniformity on the hypersphere","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i10.17037"},{"key":"ref135","first-page":"1","article-title":"Prototypical contrastive learning of unsupervised representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i9.17018"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6165"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412099"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i8.26098"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2022.05.014"},{"key":"ref141","article-title":"Integration of knowledge and data in machine learning","author":"Chen","year":"2022"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9533426"},{"key":"ref143","first-page":"16969","article-title":"Utilizing expert features for contrastive learning of time-series representations","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Nonnenmacher"},{"key":"ref144","article-title":"SleepPriorCL: Contrastive representation learning with prior knowledge-based positive mining and adaptive temperature for sleep staging","author":"Zhang","year":"2021"},{"key":"ref145","first-page":"1","article-title":"Incremental false negative detection for contrastive learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2023.10.1456"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3158069"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1145\/3439723"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref152","first-page":"1","article-title":"Large scale GAN training for high fidelity natural image synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Brock"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref154","article-title":"C-RNN-GAN: Continuous recurrent neural networks with adversarial training","author":"Mogren","year":"2016"},{"key":"ref155","first-page":"5509","article-title":"Time-Series Generative Adversarial Networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Yoon"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-09342-5_13"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/429"},{"key":"ref158","article-title":"Generating multivariate time series with Common source coordinated GAN (COSCI-GAN)","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Seyfi"},{"key":"ref159","first-page":"1","article-title":"PSA-: Progressive self attention GANs for synthetic time series","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Jeha"},{"key":"ref160","first-page":"1","article-title":"GT-GAN: General purpose time series synthesis with generative adversarial networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jeon"},{"key":"ref161","first-page":"1603","article-title":"Multivariate time series imputation with generative adversarial networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Luo"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i10.17086"},{"key":"ref163","first-page":"1","article-title":"Anomaly transformer: Time series anomaly detection with association discrepancy","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xu"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i02.5497"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i10.17070"},{"key":"ref166","first-page":"17105","article-title":"Adversarial sparse transformer for time series forecasting","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Wu"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9892791"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/616"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301834"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219845"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71368-7_8"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1145\/3055366.3055375"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17325"},{"key":"ref174","article-title":"30 years of european wind generation"},{"key":"ref175","article-title":"Electricityloaddiagrams20112014 data set","year":"2011"},{"key":"ref176","article-title":"National, regional, and state level outpatient illness and viral surveillance"},{"key":"ref177","article-title":"Weather data set"},{"key":"ref178","article-title":"Traffic data set"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210006"},{"key":"ref180","article-title":"Solar power data for integration studies"},{"key":"ref181","first-page":"1","article-title":"A public domain dataset for human activity recognition using smartphones","volume-title":"Proc. Eur. Symp. Artif. Neural Netw.","author":"Anguita"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2019.1911747"},{"key":"ref183","article-title":"The UEA multivariate time series classification archive, 2018","author":"Bagnall","year":"2018"},{"key":"ref184","doi-asserted-by":"publisher","DOI":"10.1145\/3539597.3570371"},{"key":"ref185","first-page":"1","article-title":"Pyraformer: Low-complexity pyramidal attention for long-range time series modeling and forecasting","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu"},{"key":"ref186","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539234"},{"key":"ref187","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/277"},{"key":"ref188","first-page":"1","article-title":"Scaleformer: Iterative multi-scale refining transformers for time series forecasting","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Shabani"},{"key":"ref189","first-page":"1","article-title":"Crossformer: Transformer utilizing cross-dimension dependency for multivariate time series forecasting","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang"},{"key":"ref190","first-page":"1","article-title":"Timesnet: Temporal 2d-variation modeling for general time series analysis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wu"},{"key":"ref191","first-page":"1","article-title":"MICN: Multi-scale local and global context modeling for long-term series forecasting","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6056"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-020-04748-3"},{"key":"ref194","first-page":"1","article-title":"RobustTAD: Robust time series anomaly detection via decomposition and convolutional neural networks","volume-title":"Proc. KDD Workshop Mining Learn. Time Ser.","author":"Gao"},{"key":"ref195","doi-asserted-by":"publisher","DOI":"10.1145\/3136755.3136817"},{"key":"ref196","doi-asserted-by":"publisher","DOI":"10.1016\/j.isci.2020.101656"},{"key":"ref197","article-title":"Integration of knowledge and data in machine learning","author":"Chen","year":"2022"},{"key":"ref198","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015409"},{"key":"ref199","doi-asserted-by":"publisher","DOI":"10.1145\/3448016.3452779"},{"key":"ref200","first-page":"27268","article-title":"FEDformer: Frequency enhanced decomposed transformer for long-term series forecasting","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Zhou"},{"key":"ref201","article-title":"A survey on principles, models and methods for learning from irregularly sampled time series: From discretization to attention and invariance","author":"Shukla","year":"2020"},{"key":"ref202","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i1.16145"},{"key":"ref203","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref204","first-page":"1","article-title":"Intriguing properties of neural networks","author":"Szegedy","year":"2014","journal-title":"Proc. Int. Conf. Learn. Representations"},{"key":"ref205","first-page":"1","article-title":"Robust multivariate time-series forecasting: Adversarial attacks and defense mechanisms","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu"},{"key":"ref206","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2021.11.007"},{"key":"ref207","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2986319"},{"key":"ref208","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3197190"},{"key":"ref209","first-page":"1","article-title":"Explaining and harnessing adversarial examples","author":"Goodfellow","year":"2015","journal-title":"Proc. Int. Conf. Learn. Representations"},{"key":"ref210","first-page":"1","article-title":"Making stochastic neural networks from deterministic ones","author":"Lee","year":"2017","journal-title":"Proc. Int. Conf. Learn. Representations"},{"key":"ref211","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.49"},{"key":"ref212","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.282"},{"key":"ref213","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.17"},{"key":"ref214","first-page":"5025","article-title":"Adversarial risk and the dangers of evaluating against weak attacks","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Uesato"},{"key":"ref215","article-title":"Moco SFL: Enabling cross-client collaborative self-supervised learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li"},{"key":"ref216","first-page":"1","article-title":"Unsupervised representation learning from pre-trained diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref217","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-023-00988-8"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10666888\/10496248.pdf?arnumber=10496248","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,25]],"date-time":"2025-12-25T18:26:05Z","timestamp":1766687165000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10496248\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10]]},"references-count":217,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3387317","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":[[2024,10]]}}}