{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T15:16:42Z","timestamp":1768317402163,"version":"3.49.0"},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T00:00:00Z","timestamp":1768435200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T00:00:00Z","timestamp":1768435200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T00:00:00Z","timestamp":1768435200000},"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 Internet Things J."],"published-print":{"date-parts":[[2026,1,15]]},"DOI":"10.1109\/jiot.2025.3631505","type":"journal-article","created":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T18:29:25Z","timestamp":1762885765000},"page":"3013-3025","source":"Crossref","is-referenced-by-count":0,"title":["LightSAE: Parameter-Efficient and Heterogeneity-Aware Embedding for IoT Multivariate Time Series Forecasting"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0491-5745","authenticated-orcid":false,"given":"Yi","family":"Ren","sequence":"first","affiliation":[{"name":"Department of Electrical Engineering, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9610-1524","authenticated-orcid":false,"given":"Xinjie","family":"Yu","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, Tsinghua University, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3363451"},{"key":"ref2","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":"ref3","volume-title":"Electricity Load Diagrams 2011 2014","author":"Trindade","year":"2015"},{"key":"ref4","article-title":"A time series is worth 64 words: Long-term forecasting with transformers","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Nie"},{"key":"ref5","article-title":"Revisiting long-term time series forecasting: An investigation on linear mapping","author":"Li","year":"2023","journal-title":"arXiv:2305.10721"},{"key":"ref6","article-title":"ITransformer: Inverted transformers are effective for time series forecasting","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Liu"},{"key":"ref7","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref8","article-title":"Meta-transformer: A unified framework for multimodal learning","author":"Zhang","year":"2023","journal-title":"arXiv:2307.10802"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1038\/s43247-025-02502-y"},{"key":"ref10","article-title":"Gemma 3 technical report","author":"Team","year":"2025","journal-title":"arXiv:2503.19786"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210006"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17325"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26317"},{"key":"ref14","first-page":"53140","article-title":"Unified training of universal time series forecasting transformers","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","volume":"235","author":"Woo"},{"key":"ref15","article-title":"Timer-XL: Long-context transformers for unified time series forecasting","volume-title":"Proc. 13th Int. Conf. Learn. Represent.","author":"Liu"},{"key":"ref16","article-title":"Deep time series models: A comprehensive survey and benchmark","author":"Wang","year":"2024","journal-title":"arXiv:2407.13278"},{"key":"ref17","article-title":"TimesNet: Temporal 2D-variation modeling for general time series analysis","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Wu"},{"key":"ref18","article-title":"TSMixer: An all-MLP architecture for time series forecasting","volume":"2023","author":"Chen","year":"Sep. 2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref19","article-title":"PuYun: Medium-range global weather forecasting using large kernel attention convolutional networks","author":"Zhu","year":"2024","journal-title":"arXiv:2409.02123"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557702"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3615160"},{"key":"ref22","first-page":"1","article-title":"GAFormer: Enhancing timeseries transformers through group-aware embeddings","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Xiao"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3627673.3679884"},{"key":"ref24","first-page":"4672","article-title":"Mixture-of-linear-experts for long-term time series forecasting","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Ni"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICAMechS63130.2024.10818803"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0015"},{"key":"ref27","article-title":"UniTST: Effectively modeling inter-series and intra-series dependencies for multivariate time series forecasting","volume-title":"Proc. NeurIPS Workshop Time Ser. Age Large Models","author":"Liu"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.568"},{"key":"ref29","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hu"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ita.2018.8503198"},{"key":"ref31","article-title":"LoRA training provably converges to a low-rank global minimum or it fails loudly (but it probably won\u2019t fail)","author":"Kim","year":"2025","journal-title":"arXiv:2502.09376"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.2307\/2288721"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.88"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4463"},{"key":"ref35","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"issue":"120","key":"ref36","first-page":"1","article-title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity","volume":"23","author":"Fedus","year":"2022","journal-title":"J. Mach. Learn. Res."}],"container-title":["IEEE Internet of Things Journal"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6488907\/11346825\/11240137.pdf?arnumber=11240137","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T09:19:16Z","timestamp":1768295956000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11240137\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,15]]},"references-count":36,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/jiot.2025.3631505","relation":{},"ISSN":["2327-4662","2372-2541"],"issn-type":[{"value":"2327-4662","type":"electronic"},{"value":"2372-2541","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,15]]}}}