{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T12:30:15Z","timestamp":1777984215252,"version":"3.51.4"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"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":"publisher","award":["62376153"],"award-info":[{"award-number":["62376153"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Australian Research Council Discovery","doi-asserted-by":"publisher","award":["DP240102050"],"award-info":[{"award-number":["DP240102050"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Australian Research Council Linkage Infrastructure, Equipment and Facilities","award":["LE240100131"],"award-info":[{"award-number":["LE240100131"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1109\/tnnls.2025.3571039","type":"journal-article","created":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T13:41:10Z","timestamp":1750167670000},"page":"19398-19410","source":"Crossref","is-referenced-by-count":1,"title":["Variational Hierarchical N-BEATS Model for Long-Term Time-Series Forecasting"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4891-7478","authenticated-orcid":false,"given":"Runze","family":"Yang","sequence":"first","affiliation":[{"name":"Department of Automation, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1562-9429","authenticated-orcid":false,"given":"Longbing","family":"Cao","sequence":"additional","affiliation":[{"name":"School of Computing, Macquarie University, Sydney, NSW, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4205-8561","authenticated-orcid":false,"given":"Jianxun","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Automation, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4801-7162","authenticated-orcid":false,"given":"Jie","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Automation, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.3647625"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3502289"},{"key":"ref3","first-page":"1","article-title":"Enhancing the locality and breaking the memory bottleneck of transformer on time series forecasting","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Li"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref5","article-title":"A time series is worth 64 words: Long-term forecasting with transformers","author":"Nie","year":"2022","journal-title":"arXiv:2211.14730"},{"key":"ref6","first-page":"1","article-title":"BasisFormer: Attention-based time series forecasting with learnable and interpretable basis","volume-title":"Proc. Neural Inf. Process. Syst. Conf.","author":"Ni"},{"key":"ref7","first-page":"27268","article-title":"FedFormer: Frequency enhanced decomposed transformer for long-term series forecasting","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhou"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17325"},{"key":"ref9","first-page":"22419","article-title":"Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Xu"},{"key":"ref10","first-page":"1","article-title":"Pyraformer: Low-complexity pyramidal attention for long-range time series modeling and forecasting","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Liu"},{"key":"ref11","first-page":"1","article-title":"Crossformer: Transformer utilizing cross-dimension dependency for multivariate time series forecasting","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhang"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i6.25845"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2024.111409"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2023.3322508"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TETC.2022.3230920"},{"key":"ref16","article-title":"TEMPO: Prompt-based generative pre-trained transformer for time series forecasting","author":"Cao","year":"2023","journal-title":"arXiv:2310.04948"},{"key":"ref17","first-page":"1","article-title":"Pathformer: Multi-scale transformers with adaptive pathways for time series forecasting","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Chen"},{"key":"ref18","first-page":"1","article-title":"iTransformer: Inverted transformers are effective for time series forecasting","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Liu"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26317"},{"key":"ref20","first-page":"1","article-title":"CrossGNN: Confronting noisy multivariate time series via cross interaction refinement","volume-title":"Proc. Neural Inf. Process. Syst. Conf.","author":"Huang"},{"key":"ref21","article-title":"N-BEATS: Neural basis expansion analysis for interpretable time series forecasting","author":"Oreshkin","year":"2019","journal-title":"arXiv:1905.10437"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1312.6114"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2024.3359275"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3293131"},{"key":"ref25","article-title":"Learning stochastic recurrent networks","author":"Bayer","year":"2014","journal-title":"arXiv:1411.7610"},{"key":"ref26","first-page":"1","article-title":"Sequential neural models with stochastic layers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Fraccaro"},{"key":"ref27","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":"ref28","first-page":"1651","article-title":"GP-VAE: Deep probabilistic time series imputation","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Fortuin"},{"key":"ref29","article-title":"StackVAE-G: An efficient and interpretable model for time series anomaly detection","author":"Li","year":"2021","journal-title":"arXiv:2105.08397"},{"key":"ref30","first-page":"1","article-title":"A recurrent latent variable model for sequential data","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Chung"},{"key":"ref31","first-page":"1","article-title":"ModernTCN: A modern pure convolution structure for general time series analysis","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Luo"},{"key":"ref32","article-title":"An empirical evaluation of generic convolutional and recurrent networks for sequence modeling","author":"Bai","year":"2018","journal-title":"arXiv:1803.01271"},{"key":"ref33","first-page":"5816","article-title":"SCINet: Time series modeling and forecasting with sample convolution and interaction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Liu"},{"key":"ref34","first-page":"1","article-title":"MICN: Multi-scale local and global context modeling for long-term series forecasting","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Wang"},{"key":"ref35","first-page":"1","article-title":"Unsupervised scalable representation learning for multivariate time series","volume-title":"Proc. Neural Inf. Process. Syst. Conf.","volume":"32","author":"Franceschi"},{"key":"ref36","first-page":"1","article-title":"Think globally, act locally: A deep neural network approach to high-dimensional time series forecasting","volume-title":"Proc. Neural Inf. Process. Syst. Conf.","volume":"32","author":"Sen"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref38","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"Chung","year":"2014","journal-title":"arXiv:1412.3555"},{"key":"ref39","first-page":"1","article-title":"Deep state space models for time series forecasting","volume-title":"Proc. Neural Inf. Process. Syst. Conf.","volume":"31","author":"Rangapuram"},{"key":"ref40","first-page":"1","article-title":"Dilated recurrent neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Chang"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.energy.2021.120455"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413914"},{"key":"ref43","first-page":"1","article-title":"WITRAN: Water-wave information transmission and recurrent acceleration network for long-range time series forecasting","volume-title":"Proc. Neural Inf. Process. Syst. Conf.","author":"Jia"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijforecast.2019.07.001"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i6.25854"},{"key":"ref46","first-page":"1","article-title":"Frequency-domain MLPs are more effective learners in time series forecasting","volume-title":"Proc. Neural Inf. Process. Syst. Conf.","author":"Yi"},{"key":"ref47","article-title":"TimeMixer: Decomposable multiscale mixing for time series forecasting","author":"Wang","year":"2024","journal-title":"arXiv:2405.14616"},{"key":"ref48","first-page":"1","article-title":"Bayesian federated learning: A survey","volume-title":"Proc. Int. Joint Conf. Artif. Intell.","author":"Cao"},{"key":"ref49","article-title":"The concrete distribution: A continuous relaxation of discrete random variables","author":"Maddison","year":"2016","journal-title":"arXiv:1611.00712"},{"key":"ref50","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11195929\/11038824.pdf?arnumber=11038824","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T18:41:29Z","timestamp":1765219289000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11038824\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":50,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2025.3571039","relation":{"has-preprint":[{"id-type":"doi","id":"10.36227\/techrxiv.24417700.v1","asserted-by":"object"}]},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10]]}}}