{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T20:06:05Z","timestamp":1780949165887,"version":"3.54.1"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2023YFC3305600"],"award-info":[{"award-number":["2023YFC3305600"]}]},{"name":"National Key R&D Program of China","award":["2018YFA0704000"],"award-info":[{"award-number":["2018YFA0704000"]}]},{"name":"National Key R&D Program of China","award":["NSFC"],"award-info":[{"award-number":["NSFC"]}]},{"name":"National Key R&D Program of China","award":["62021002"],"award-info":[{"award-number":["62021002"]}]},{"DOI":"10.13039\/501100004731","name":"Zhejiang Provincial Natural Science Foundation","doi-asserted-by":"crossref","award":["LDT23F02024F02"],"award-info":[{"award-number":["LDT23F02024F02"]}],"id":[{"id":"10.13039\/501100004731","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Key Research and Development Project of Tibet Autonomous Region","award":["XZ202101ZY0019G"],"award-info":[{"award-number":["XZ202101ZY0019G"]}]},{"name":"THUIBCS, Tsinghua University"},{"name":"BLBCI, Beijing Municipal Education Commission"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Biomed. Health Inform."],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1109\/jbhi.2025.3592452","type":"journal-article","created":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T17:56:23Z","timestamp":1753379783000},"page":"4646-4657","source":"Crossref","is-referenced-by-count":0,"title":["MAT: Mixing Attention Transfer From Multiple Transformers for Medical Tasks"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1391-9142","authenticated-orcid":false,"given":"Zi-Hao","family":"Bo","sequence":"first","affiliation":[{"name":"BNRist and School of Software, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9808-9805","authenticated-orcid":false,"given":"Yuchen","family":"Guo","sequence":"additional","affiliation":[{"name":"BNRist and Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangru","family":"Chen","sequence":"additional","affiliation":[{"name":"Intelligent Medical Research Department, Hangzhou Zhuoxi Institute of Brain and Intelligence, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Xie","sequence":"additional","affiliation":[{"name":"BNRist and School of Software, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lishan","family":"Ye","sequence":"additional","affiliation":[{"name":"BNRist and Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0953-1057","authenticated-orcid":false,"given":"Feng","family":"Xu","sequence":"additional","affiliation":[{"name":"BNRist and School of Software, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-08999-2_22"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06291-2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2022.104227"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-018-0272-7"},{"key":"ref5","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Vaswani","year":"2017"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102802"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.imed.2022.07.002"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3152247"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3505244"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.210284"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1002\/widm.1249"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2017.09.005"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-019-8208-z"},{"key":"ref14","first-page":"32913","article-title":"Hub-pathway: Transfer learning from a hub of pre-trained models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Shu","year":"2022"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00148"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803726"},{"key":"ref17","first-page":"7294","article-title":"LEEP: A new measure to evaluate transferability of learned representations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nguyen","year":"2020"},{"key":"ref18","first-page":"12133","article-title":"LogME: Practical assessment of pre-trained models for transfer learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"You","year":"2021"},{"key":"ref19","first-page":"19301","article-title":"Scalable diverse model selection for accessible transfer learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Bolya","year":"2021"},{"key":"ref20","first-page":"25739","article-title":"Deep model reassembly","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Yang","year":"2022"},{"key":"ref21","article-title":"Knowledge flow: Improve upon your teachers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu","year":"2019"},{"key":"ref22","first-page":"9626","article-title":"Zoo-tuning: Adaptive transfer from a Zoo of models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Shu","year":"2021"},{"key":"ref23","first-page":"23965","article-title":"Model soups: Averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wortsman","year":"2022"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"ref25","first-page":"22045","article-title":"Model fusion via optimal transport","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Singh","year":"2020"},{"key":"ref26","article-title":"Git re-basin: Merging models modulo permutation symmetries","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Ainsworth","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10097156"},{"key":"ref28","article-title":"Zipit! merging models from different tasks without training","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Stoica","year":"2024"},{"key":"ref29","article-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Shazeer","year":"2017"},{"key":"ref30","article-title":"GShard: Scaling giant models with conditional computation and automatic sharding","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lepikhin","year":"2021"},{"issue":"1","key":"ref31","first-page":"5232","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":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-478"},{"issue":"PMLR","key":"ref33","first-page":"5547","article-title":"GLaM: Efficient scaling of language models with mixture-of-experts","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Du","year":"2022"},{"key":"ref34","article-title":"Scalable transfer learning with expert models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Puigcerver","year":"2021"},{"key":"ref35","first-page":"8583","article-title":"Scaling vision with sparse mixture of experts","volume":"34","author":"Riquelme","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref36","first-page":"9564","article-title":"Multimodal contrastive learning with LIMoE: The language-image mixture of experts","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Mustafa","year":"2022"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657722"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72390-2_58"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2025.3540809"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ipdpsw55747.2022.00171"},{"key":"ref41","article-title":"A review of sparse expert models in deep learning","author":"Fedus","year":"2022"},{"key":"ref42","article-title":"Better plain VIT baselines for imagenet-1 K","author":"Beyer","year":"2022"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref44","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"issue":"5","key":"ref45","first-page":"7","article-title":"Reading digits in natural images with unsupervised feature learning","volume-title":"Proc. NIPS Workshop Deep Learn. Unsupervised Feature Learn.","volume":"2011","author":"Netzer","year":"2011"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00020"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2021.3125459"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2018.161"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-25138-w"},{"key":"ref50","article-title":"mixup: Beyond empirical risk minimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang","year":"2018"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.14569\/IJACSA.2021.0120670"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-1803"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1101\/2020.04.13.20063941"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/IEMBS.2010.5626137"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.112057"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43898-1_11"}],"container-title":["IEEE Journal of Biomedical and Health Informatics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6221020\/11552637\/11095631.pdf?arnumber=11095631","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T19:53:16Z","timestamp":1780948396000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11095631\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":57,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/jbhi.2025.3592452","relation":{},"ISSN":["2168-2194","2168-2208"],"issn-type":[{"value":"2168-2194","type":"print"},{"value":"2168-2208","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6]]}}}