{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,10]],"date-time":"2026-10-10T13:40:40Z","timestamp":1791639640707,"version":"4.3.4"},"reference-count":82,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62276130"],"award-info":[{"award-number":["62276130"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"National Key Research and Development Program of China","award":["2023YFF1204803"],"award-info":[{"award-number":["2023YFF1204803"]}]},{"name":"Key Research and Development Plan of Jiangsu Province","award":["BE2022842"],"award-info":[{"award-number":["BE2022842"]}]},{"name":"Ministry of Education, Singapore, under its MOE Tier 1","award":["SKI 2021_08_03"],"award-info":[{"award-number":["SKI 2021_08_03"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1109\/tnnls.2026.3673975","type":"journal-article","created":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T20:06:50Z","timestamp":1775678810000},"page":"4770-4784","source":"Crossref","is-referenced-by-count":2,"title":["Bridging Distribution Gaps in Time Series Foundation Model Pretraining With Prototype-Guided Normalization"],"prefix":"10.1109","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2611-3145","authenticated-orcid":false,"given":"Peiliang","family":"Gong","sequence":"first","affiliation":[{"name":"Nanjing University of Aeronautics and Astronautics","place":["Nanjing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9282-0991","authenticated-orcid":false,"given":"Emadeldeen","family":"Eldele","sequence":"additional","affiliation":[{"name":"Khalifa University","place":["Abu Dhabi, United Arab Emirates"],"department":["Department of Computer Science"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0977-3600","authenticated-orcid":false,"given":"Min","family":"Wu","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research (I<sup>2<\/sup>R), Agency for Science, Technology and Research (A*STAR)","place":["Singapore, Singapore"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1719-0328","authenticated-orcid":false,"given":"Zhenghua","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Glasgow","place":["Glasgow, U.K."]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0762-6562","authenticated-orcid":false,"given":"Xiaoli","family":"Li","sequence":"additional","affiliation":[{"name":"Singapore University of Technology and Design","place":["Tampines, Singapore"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5658-7643","authenticated-orcid":false,"given":"Daoqiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Nanjing University of Aeronautics and Astronautics","place":["Nanjing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s13042-024-02443-6"},{"key":"ref2","first-page":"2","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NaacL-HLT","volume":"1","author":"Kenton"},{"key":"ref3","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"arXiv:2005.14165"},{"key":"ref4","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref5","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-industry.69"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-05881-4"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00667-9"},{"key":"ref9","first-page":"1","article-title":"Reversible instance normalization for accurate time-series forecasting against distribution shift","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kim"},{"key":"ref10","article-title":"Deep time series models: A comprehensive survey and benchmark","author":"Wang","year":"2024","journal-title":"arXiv:2407.13278"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671451"},{"key":"ref12","article-title":"TEMPO: Prompt-based generative pre-trained transformer for time series forecasting","author":"Cao","year":"2023","journal-title":"arXiv:2310.04948"},{"key":"ref13","article-title":"Lag-llama: Towards foundation models for probabilistic time series forecasting","author":"Rasul","year":"2023","journal-title":"arXiv:2310.08278"},{"key":"ref14","article-title":"Units: Building a unified time series model","author":"Gao","year":"2024","journal-title":"arXiv:2403.00131"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1877"},{"key":"ref16","article-title":"UniCL: A universal contrastive learning framework for large time series models","author":"Li","year":"2024","journal-title":"arXiv:2405.10597"},{"key":"ref17","first-page":"10148","article-title":"A decoder-only foundation model for time-series forecasting","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Das"},{"key":"ref18","first-page":"32369","article-title":"Timer: Generative pre-trained transformers are large time series models","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Liu"},{"key":"ref19","first-page":"11412","article-title":"Timesiam: A pre-training framework for Siamese time-series modeling","volume-title":"Proc. ICML","author":"Dong"},{"key":"ref20","first-page":"16115","article-title":"MOMENT: A family of open time-series foundation models","volume-title":"Proc. Forty-first Int. Conf. Mach. Learn.","author":"Goswami"},{"key":"ref21","article-title":"Ti-MAE: Self-supervised masked time series autoencoders","author":"Li","year":"2023","journal-title":"arXiv:2301.08871"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3308189"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3615155"},{"key":"ref24","first-page":"1","article-title":"Learning to embed time series patches independently","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Lee"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1306"},{"key":"ref26","first-page":"1","article-title":"A time series is worth 64 words: Long-term forecasting with transformers","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Nie"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1201\/9781003616719-3"},{"key":"ref28","first-page":"53140","article-title":"Unified training of universal time series forecasting transformers","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Woo"},{"issue":"10","key":"ref29","first-page":"1","article-title":"Chronos: Learning the language of time series","volume":"2024","author":"Ansari","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref30","first-page":"1","article-title":"Time-moe: Billion-scale time series foundation models with mixture of experts","volume-title":"Proc. 13th Int. Conf. Learn. Represent.","author":"Xiaoming"},{"key":"ref31","first-page":"39295","article-title":"Sundial: A family of highly capable time series foundation models","volume-title":"Proc. 42nd Int. Conf. Mach. Learn.","author":"Liu"},{"key":"ref32","first-page":"64127","article-title":"Towards a general time series forecasting model with unified representation and adaptive transfer","volume-title":"Proc. 42nd Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref33","first-page":"43248","article-title":"Enhancing foundation models for time series forecasting via wavelet-based tokenization","volume-title":"Proc. 42nd Int. Conf. Mach. Learn.","author":"Masserano"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.energy.2006.11.014"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3587937"},{"key":"ref36","first-page":"12746","article-title":"Domain adaptation for time series under feature and label shifts","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"He"},{"key":"ref37","article-title":"Evidentially calibrated source-free time-series domain adaptation with temporal imputation","author":"Ragab","year":"2024","journal-title":"arXiv:2406.02635"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548167"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3643035"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3355212"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482315"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0718"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i6.25914"},{"key":"ref44","article-title":"IN-flow: Instance normalization flow for non-stationary time series forecasting","author":"Fan","year":"2024","journal-title":"arXiv:2401.16777"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671926"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2010.5596746"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2944933"},{"key":"ref48","first-page":"51","article-title":"Selective review on adaptive normalization techniques","volume-title":"Proc. Workshop Intell. Syst.","author":"Panday"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00811"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.03.005"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00753"},{"key":"ref52","first-page":"4778","article-title":"Beyond batchnorm: Towards a unified understanding of normalization in deep learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Lubana"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467330"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412547"},{"key":"ref55","first-page":"1891","article-title":"Extended deep adaptive input normalization for preprocessing time series data for neural networks","volume-title":"Proc. AISTATS","author":"September"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0628"},{"key":"ref57","first-page":"17437","article-title":"Sin: Selective and interpretable normalization for long-term time series forecasting","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Han"},{"key":"ref58","article-title":"Layer normalization","author":"Lei Ba","year":"2016","journal-title":"arXiv:1607.06450"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref60","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref61","first-page":"2988","article-title":"Asymmetric tri-training for unsupervised domain adaptation","volume-title":"Proc. 34th Int. Conf. Mach. Learn. (ICML)","volume":"70","author":"Saito"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2019.1911747"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1016\/j.ymssp.2015.04.021"},{"key":"ref65","first-page":"1","article-title":"PRONOSTIA: An experimental platform for bearings accelerated degradation tests","volume-title":"Proc. IEEE Int. Conf. Prognostics Health Manag.","author":"Nectoux"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TR.2018.2882682"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1016\/j.jsv.2005.03.007"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1016\/j.dib.2018.11.019"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.36001\/phme.2016.v3i1.1577"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/2809695.2809718"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/MPRV.2008.40"},{"key":"ref72","first-page":"3","article-title":"A public domain dataset for human activity recognition using smartphones","volume-title":"Proc. Esann","volume":"3","author":"Anguita"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1145\/2370216.2370438"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1145\/1964897.1964918"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219845"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467174"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330672"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CySWater.2016.7469060"},{"key":"ref79","article-title":"Monash time series forecasting archive","author":"Godahewa","year":"2021","journal-title":"arXiv:2105.06643"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210006"},{"key":"ref81","first-page":"22419","article-title":"Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting","volume-title":"Proc. NIPS","volume":"34","author":"Wu"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.04.070"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11676227\/11477883.pdf?arnumber=11477883","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T19:20:02Z","timestamp":1788808802000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11477883\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":82,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2026.3673975","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9]]}}}