{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T21:01:41Z","timestamp":1769634101561,"version":"3.49.0"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2025.3649490","type":"journal-article","created":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T18:38:53Z","timestamp":1767119933000},"page":"11505-11533","source":"Crossref","is-referenced-by-count":0,"title":["Learnable Temporal Sparse Memory iTransformer: Revisiting Sparsity and Memory in Transformers"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-9696-7276","authenticated-orcid":false,"given":"Polycarp Shizawaliyi","family":"Yakoi","sequence":"first","affiliation":[{"name":"Liaoning Technical University, Huludao, Liaoning, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7879-2368","authenticated-orcid":false,"given":"Xiangfu","family":"Meng","sequence":"additional","affiliation":[{"name":"Liaoning Technical University, Huludao, Liaoning, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7364-046X","authenticated-orcid":false,"given":"Chunlin","family":"Yu","sequence":"additional","affiliation":[{"name":"Liaoning Technical University, Huludao, Liaoning, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6765-957X","authenticated-orcid":false,"given":"Victor Adeyi","family":"Odeh","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9958-8320","authenticated-orcid":false,"given":"Danladi","family":"Suleman","sequence":"additional","affiliation":[{"name":"School of Science, Technology and Engineering, University of the Sunshine Coast, UniSC Moreton Bay, Sippy Downs1, QLD, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6687-6214","authenticated-orcid":false,"given":"Yongqin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Liaoning Technical University, Huludao, Liaoning, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5260-1105","authenticated-orcid":false,"given":"Xiaoyan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Liaoning Technical University, Huludao, Liaoning, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-89929-5_5"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref5","article-title":"On the opportunities and risks of foundation models","author":"Bommasani","year":"2021","journal-title":"arXiv:2108.07258"},{"key":"ref6","first-page":"5220","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"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17325"},{"key":"ref8","article-title":"Compressive transformers for long-range sequence modelling","author":"Rae","year":"2019","journal-title":"arXiv:1911.05507"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-aacl.29"},{"key":"ref10","first-page":"4004","article-title":"iTransformer: Inverted transformers are effective for time series forecasting","volume-title":"Proc. ICLR","author":"Liu"},{"key":"ref11","first-page":"22419","article-title":"Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Wu"},{"key":"ref12","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":"ref13","article-title":"A time series is worth 64 words: Long-term forecasting with transformers","author":"Nie","year":"2022","journal-title":"arXiv:2211.14730"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CNIOT65435.2025.11070699"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CNIOT65435.2025.11070962"},{"key":"ref16","article-title":"Generating long sequences with sparse transformers","author":"Child","year":"2019","journal-title":"arXiv:1904.10509"},{"key":"ref17","article-title":"Reformer: The efficient transformer","author":"Kitaev","year":"2020","journal-title":"arXiv:2001.04451"},{"key":"ref18","article-title":"Longformer: The long-document transformer","author":"Beltagy","year":"2020","journal-title":"arXiv:2004.05150"},{"key":"ref19","first-page":"17283","article-title":"Big bird: Transformers for longer sequences","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zaheer"},{"key":"ref20","article-title":"Neural Turing machines","author":"Graves","year":"2014","journal-title":"arXiv:1410.5401"},{"key":"ref21","article-title":"Memory networks","author":"Weston","year":"2014","journal-title":"arXiv:1410.3916"},{"key":"ref22","first-page":"1842","article-title":"Meta-learning with memory-augmented neural networks","volume-title":"Proc. 33rd Int. Conf. Mach. Learn.","author":"Santoro"},{"key":"ref23","article-title":"Memory transformer","author":"Burtsev","year":"2020","journal-title":"arXiv:2006.11527"},{"key":"ref24","article-title":"Long-term forecasting with TiDE: Time-series dense encoder","author":"Das","year":"2023","journal-title":"arXiv:2304.08424"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26317"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3390\/math11020476"},{"key":"ref27","article-title":"CINFormer: Transformer network with multi-stage CNN feature injection for surface defect segmentation","author":"Jiang","year":"2023","journal-title":"arXiv:2309.12639"},{"key":"ref28","first-page":"23803","article-title":"Cross-entropy loss functions: Theoretical analysis and applications","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mao"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32520-6_22"},{"key":"ref30","article-title":"Convergence rates for the Adam optimizer","author":"Dereich","year":"2024","journal-title":"arXiv:2407.21078"},{"key":"ref31","first-page":"9881","article-title":"Non-stationary transformers: Exploring the stationarity in time series forecasting","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref32","first-page":"1","article-title":"Crossformer: Transformer utilizing cross-dimension dependency for multivariate time series forecasting","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Zhang"},{"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.","author":"Liu"},{"key":"ref34","article-title":"TimesNet: Temporal 2D-variation modeling for general time series analysis","author":"Wu","year":"2022","journal-title":"arXiv:2210.02186"},{"key":"ref35","article-title":"Diffusion convolutional recurrent neural network: Data-driven traffic forecasting","author":"Li","year":"2017","journal-title":"arXiv:1707.01926"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1995.7.1.108"},{"issue":"1","key":"ref37","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390294"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref40","article-title":"Benchmarking neural network robustness to common corruptions and perturbations","author":"Hendrycks","year":"2019","journal-title":"arXiv:1903.12261"},{"key":"ref41","volume-title":"What Is a Transformer Model?","author":"Merritt","year":"2022"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-49409-8_7"},{"key":"ref43","article-title":"An image is worth 16$\\times$\n16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref44","article-title":"Revisiting long-term time series forecasting: An investigation on linear mapping","author":"Li","year":"2023","journal-title":"arXiv:2305.10721"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-814761-0.00012-5"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-385208-3.00014-6"},{"key":"ref47","volume-title":"Time Series Transformer","author":"Rasul","year":"2025"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11318337.pdf?arnumber=11318337","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T05:59:44Z","timestamp":1769493584000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11318337\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3649490","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}