{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,26]],"date-time":"2025-08-26T22:10:06Z","timestamp":1756246206453,"version":"3.44.0"},"reference-count":78,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"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 Trans. Knowl. Data Eng."],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1109\/tkde.2025.3573673","type":"journal-article","created":{"date-parts":[[2025,6,2]],"date-time":"2025-06-02T14:03:35Z","timestamp":1748873015000},"page":"4604-4619","source":"Crossref","is-referenced-by-count":0,"title":["Gaussian Process Latent Variable Modeling for Few-Shot Time Series Forecasting"],"prefix":"10.1109","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1819-4056","authenticated-orcid":false,"given":"Yunyao","family":"Cheng","sequence":"first","affiliation":[{"name":"Department of Computer Science, Aalborg University, Aalborg, Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4516-4637","authenticated-orcid":false,"given":"Chenjuan","family":"Guo","sequence":"additional","affiliation":[{"name":"Department of Computer Science, East China Normal University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3904-0395","authenticated-orcid":false,"given":"Kaixuan","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Aalborg University, Aalborg, Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5159-2312","authenticated-orcid":false,"given":"Kai","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Aalborg University, Aalborg, Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1658-1079","authenticated-orcid":false,"given":"Bin","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, East China Normal University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiandong","family":"Xie","sequence":"additional","affiliation":[{"name":"Huawei Cloud Database Innovation Lab, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9697-7670","authenticated-orcid":false,"given":"Christian S.","family":"Jensen","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Aalborg University, Aalborg, Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8842-0879","authenticated-orcid":false,"given":"Feiteng","family":"Huang","sequence":"additional","affiliation":[{"name":"Huawei Cloud Database Innovation Lab, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0217-3998","authenticated-orcid":false,"given":"Kai","family":"Zheng","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29872"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.2196\/55577"},{"article-title":"Sequential latent variable models for few-shot high-dimensional time-series forecasting","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Jiang","key":"ref3"},{"article-title":"Which priors matter? Benchmarking models for learning latent dynamics","volume-title":"Proc. Neural Inf. Process. Syst. Track Datasets Benchmarks","author":"Botev","key":"ref4"},{"key":"ref5","first-page":"3601","article-title":"A disentangled recognition and nonlinear dynamics model for unsupervised learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Fraccaro"},{"article-title":"Deep variational bayes filters: Unsupervised learning of state space models from raw data","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Karl","key":"ref6"},{"article-title":"A time series is worth 64 words: Long-term forecasting with transformers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Nie","key":"ref7"},{"key":"ref8","first-page":"2980","article-title":"A recurrent latent variable model for sequential data","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chung"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10779"},{"article-title":"PDE-driven spatiotemporal disentanglement","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Don\u00e1","key":"ref10"},{"article-title":"Generalised Gaussian process latent variable models (GPLVM) with stochastic variational inference","year":"2022","author":"Lalchand","key":"ref11"},{"key":"ref12","first-page":"21640","article-title":"Meta-learning dynamics forecasting using task inference","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i10.17115"},{"key":"ref14","first-page":"5243","article-title":"Enhancing the locality and breaking the memory bottleneck of transformer on time series forecasting","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"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":"ref15"},{"article-title":"Pathformer: Multi-scale transformers with Adaptive Pathways for Time Series Forecasting","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen","key":"ref16"},{"article-title":"Crossformer: Transformer utilizing cross-dimension dependency for multivariate time series forecasting","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang","key":"ref17"},{"article-title":"CARD: Channel aligned robust blend transformer for time series forecasting","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang","key":"ref18"},{"article-title":"ITransformer: Inverted transformers are effective for time series forecasting","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijforecast.2019.02.011"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i6.25863"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i1.16145"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599879"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-16145-3_3"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220060"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/264"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.14778\/3494124.3494142"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijforecast.2021.03.012"},{"key":"ref29","first-page":"22419","article-title":"Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wu"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17325"},{"key":"ref31","first-page":"17804","article-title":"Adaptive graph convolutional recurrent network for traffic forecasting","volume-title":"Proc. Adv. in Neural Inf. Process. Syst.","author":"Bai"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE51399.2021.00153"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098037"},{"key":"ref34","first-page":"17766","article-title":"Spectral temporal graph neural network for multivariate time-series forecasting","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Cao"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/277"},{"key":"ref37","first-page":"1067","article-title":"Gaussian process kernels for pattern discovery and extrapolation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wilson"},{"key":"ref38","first-page":"6285","article-title":"Discovering latent covariance structures for multiple time series","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tong"},{"article-title":"Randomized automatic differentiation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Oktay","key":"ref39"},{"volume-title":"Gaussian Processes for Machine Learning","year":"2006","author":"Williams","key":"ref40"},{"volume-title":"Covariance Kernels for Fast Automatic Pattern Discovery and Extrapolation With Gaussian Processes","year":"2014","author":"Wilson","key":"ref41"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/3206.001.0001"},{"key":"ref43","article-title":"Automatic model construction with Gaussian processes","volume-title":"Comput. Biological Learn. Lab.","author":"Duvenaud","year":"2014"},{"key":"ref44","first-page":"2850","article-title":"Learning scalable deep kernels with recurrent structure","volume":"18","author":"Al-Shedivat","year":"2017","journal-title":"J. Mach. Learn. Res."},{"key":"ref45","first-page":"1166","article-title":"Structure discovery in nonparametric regression through compositional kernel search","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Duvenaud"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2014.2333664"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-84858-7"},{"key":"ref48","first-page":"306","article-title":"Exploiting compositionality to explore a large space of model structures","volume-title":"PRoc. Conf. Uncertainty Artif. Intell.","author":"Grosse"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v28i1.8904"},{"article-title":"DARTS: Differentiable architecture search","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu","key":"ref50"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.14778\/3503585.3503604"},{"key":"ref52","first-page":"6684","article-title":"Spectral mixture kernels for multi-output Gaussian processes","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Parra"},{"key":"ref53","first-page":"2594","article-title":"Stochastic variational deep kernel learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wilson"},{"key":"ref54","first-page":"370","article-title":"Deep kernel learning","volume-title":"Proc. Conf. Artif. Intell. Statist.","author":"Wilson"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijforecast.2018.06.001"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2019.1911747"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.enbuild.2014.04.034"},{"article-title":"Diffusion convolutional recurrent neural network: Data-driven traffic forecasting","year":"2017","author":"Li","key":"ref58"},{"key":"ref59","first-page":"2494","article-title":"Exploring interpretable LSTM neural networks over multi-variable data","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Guo"},{"article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","key":"ref60"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2015.12.061"},{"key":"ref62","first-page":"6441","article-title":"Benchmarking deep learning interpretability in time series predictions","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ismail"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijforecast.2003.09.015"},{"key":"ref64","first-page":"789","article-title":"Deep sigma point processes","volume-title":"Proc. Conf. Uncertainty Artif. Intell.","author":"Jankowiak"},{"key":"ref65","first-page":"4591","article-title":"Doubly stochastic variational inference for deep Gaussian processes","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Salimbeni"},{"key":"ref66","first-page":"207","article-title":"Deep Gaussian processes","volume-title":"Proc. Conf. Artif. Intell. Statist.","author":"Damianou"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.5555\/2981562.2981582"},{"key":"ref68","first-page":"1139","article-title":"Gaussian process regression networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wilson"},{"key":"ref69","first-page":"2339","article-title":"Spike and slab variational inference for multi-task and multiple kernel learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Titsias"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-25751-8_76"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1016\/j.cogpsych.2017.11.002"},{"key":"ref72","first-page":"575","article-title":"Scaling up the automatic statistician: Scalable structure discovery using Gaussian processes","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Kim"},{"key":"ref73","first-page":"3267","article-title":"Structured variationally auto-encoded optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lu"},{"key":"ref74","first-page":"4828","article-title":"Differentiable compositional kernel learning for Gaussian processes","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sun"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE53745.2022.00273"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2021.3100641"},{"key":"ref77","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":"ref78","first-page":"1775","article-title":"Kernel interpolation for scalable structured Gaussian processes (KISS-GP)","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wilson"}],"container-title":["IEEE Transactions on Knowledge and Data Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/69\/11072530\/11020984.pdf?arnumber=11020984","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,26]],"date-time":"2025-08-26T21:54:50Z","timestamp":1756245290000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11020984\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8]]},"references-count":78,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tkde.2025.3573673","relation":{},"ISSN":["1041-4347","1558-2191","2326-3865"],"issn-type":[{"type":"print","value":"1041-4347"},{"type":"electronic","value":"1558-2191"},{"type":"electronic","value":"2326-3865"}],"subject":[],"published":{"date-parts":[[2025,8]]}}}