{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T21:08:59Z","timestamp":1783976939563,"version":"3.55.0"},"reference-count":61,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["ERC-ASPIRE-1941524"],"award-info":[{"award-number":["ERC-ASPIRE-1941524"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["DUE-2216396"],"award-info":[{"award-number":["DUE-2216396"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000138","name":"U.S. Department of Education","doi-asserted-by":"publisher","award":["P116S210004"],"award-info":[{"award-number":["P116S210004"]}],"id":[{"id":"10.13039\/100000138","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000138","name":"U.S. Department of Education","doi-asserted-by":"publisher","award":["P120A220044"],"award-info":[{"award-number":["P120A220044"]}],"id":[{"id":"10.13039\/100000138","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Big Data"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1109\/tbdata.2026.3689009","type":"journal-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:52:30Z","timestamp":1777492350000},"page":"1401-1419","source":"Crossref","is-referenced-by-count":0,"title":["GeMeR-TS: Generative Memory-Based Retrieval and Mixture-of-Experts for Cross-Domain Time-Series Forecasting"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5308-8531","authenticated-orcid":false,"given":"Chin-Yi","family":"Lin","sequence":"first","affiliation":[{"name":"Department of Industrial Manufacturing and Systems Engineering, University of Texas at El Paso, El Paso, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4762-1727","authenticated-orcid":false,"given":"Solayman Hossain","family":"Emon","sequence":"additional","affiliation":[{"name":"Computational Science Program, University of Texas, EL Paso, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3903-529X","authenticated-orcid":false,"given":"Tzu-Liang","family":"Tseng","sequence":"additional","affiliation":[{"name":"Department of Industrial Manufacturing and Systems Engineering, University of Texas at El Paso, El Paso, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1","article-title":"Retrieval based time series forecasting","volume-title":"Proc. CIKM Workshop Appl. Mach. Learn. Methods Time Ser. Forecasting","author":"Jing","year":"2022"},{"key":"ref2","first-page":"1","article-title":"TS-RAG: Retrieval-augmented generation based time series foundation models are stronger zero-shot forecaster","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"38","author":"Ning"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijforecast.2021.11.013"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2025\/1173"},{"key":"ref5","article-title":"TimeEmb: A lightweight static-dynamic disentanglement framework for time series forecasting","author":"Xia","year":"2025"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3817600"},{"issue":"120","key":"ref7","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."},{"key":"ref8","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive NLP tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Lewis"},{"key":"ref9","article-title":"Chronos: Learning the language of time series","author":"Ansari","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref10","article-title":"Lag-Llama: Towards foundation models for time series forecasting","volume-title":"Proc. NeurIPS Workshop Robustness Zero\/Few-Shot Learn. Large Foundation Models","author":"Rasul"},{"key":"ref11","article-title":"TimeGPT-1","author":"Garza","year":"2023"},{"key":"ref12","article-title":"TSMixer: An all-MLP architecture for time series forecasting","author":"Chen","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref13","article-title":"A time series is worth 64 words: Long-term forecasting with Transformers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Nie"},{"key":"ref14","article-title":"TimesNet: Temporal 2D-variation modeling for general time series analysis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wu"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1201\/9781003612742-2"},{"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","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0718"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26317"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1201\/9781003616719-7"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20881"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/icde65448.2025.00237"},{"key":"ref22","first-page":"10280","article-title":"Domain adaptation for time series forecasting via attention sharing","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","volume":"162","author":"Jin"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17325"},{"key":"ref24","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":"Wu"},{"key":"ref25","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":"ref26","doi-asserted-by":"publisher","DOI":"10.1201\/9781003612742-2"},{"key":"ref27","article-title":"ETSformer: Exponential smoothing Transformers for time-series forecasting","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Woo"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26317"},{"key":"ref29","article-title":"A time series is worth 64 words: Long-term forecasting with Transformers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Nie"},{"key":"ref30","article-title":"N-BEATS: Neural basis expansion analysis for interpretable time series forecasting","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Oreshkin"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i6.25854"},{"key":"ref32","article-title":"TimeGPT-1","author":"Garza","year":"2023"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1080\/00031305.2017.1380080"},{"key":"ref34","first-page":"16115","article-title":"MOMENT: A family of open time-series foundation models","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","volume":"235","author":"Goswami"},{"key":"ref35","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":"ref36","first-page":"10148","article-title":"A decoder-only foundation model for time-series forecasting","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","volume":"235","author":"Das"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671451"},{"key":"ref38","article-title":"Efficiently modeling long sequences with structured state spaces","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gu"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/479"},{"key":"ref40","first-page":"3929","article-title":"REALM: Retrieval-augmented language model pre-training","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","volume":"119","author":"Guu"},{"key":"ref41","article-title":"Retrieval augmented time series forecasting","author":"Han","year":"2025"},{"key":"ref42","first-page":"1","article-title":"TS-RAG: Retrieval-augmented generation based time series foundation models are stronger zero-shot forecaster","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"38","author":"Ning"},{"key":"ref43","article-title":"Reversible instance normalization for accurate time-series forecasting against distribution shift","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kim"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1201\/9781003616719-7"},{"issue":"120","key":"ref45","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."},{"key":"ref46","article-title":"Time-MoE: Billion-scale time series foundation models with mixture of experts","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Shi"},{"key":"ref47","article-title":"MoE-RAFM: A large-scale time-series foundation model with mixture-ofexperts and retrieval-augmented mechanisms","author":"Lin","year":"2025","journal-title":"IEEE Trans. Artif. Intell."},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijforecast.2019.07.001"},{"key":"ref49","article-title":"Long-term forecasting with TiDE: Time-series dense encoder","author":"Das","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-009-5152-4"},{"key":"ref51","article-title":"Deep variational information bottleneck","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Alemi"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s00365-021-09546-1"},{"key":"ref53","article-title":"Mixed precision training","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Micikevicius"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1189"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/324"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijforecast.2021.03.012"},{"key":"ref58","article-title":"FlashAttention-2: Faster attention with better parallelism and work partitioning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dao"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.05957"},{"key":"ref60","first-page":"10524","article-title":"On layer normalization in the Transformer architecture","volume-title":"Proc. 37thInt. Conf. Mach. Learn","volume":"119","author":"Xiong"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i18.34067"}],"container-title":["IEEE Transactions on Big Data"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/6687317\/11603878\/11499420-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6687317\/11603878\/11499420.pdf?arnumber=11499420","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T20:06:17Z","timestamp":1783973177000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11499420\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":61,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tbdata.2026.3689009","relation":{},"ISSN":["2332-7790","2372-2096"],"issn-type":[{"value":"2332-7790","type":"electronic"},{"value":"2372-2096","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8]]}}}