{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T16:04:09Z","timestamp":1781280249127,"version":"3.54.1"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"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":["62172068"],"award-info":[{"award-number":["62172068"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62172071"],"award-info":[{"award-number":["62172071"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province","doi-asserted-by":"publisher","award":["ZR2023LZH008"],"award-info":[{"award-number":["ZR2023LZH008"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province","doi-asserted-by":"publisher","award":["ZR2023LZH013"],"award-info":[{"award-number":["ZR2023LZH013"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province","doi-asserted-by":"publisher","award":["ZR2023LZH016"],"award-info":[{"award-number":["ZR2023LZH016"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]},{"name":"joint research project with China Coal Research Institute","award":["2022-3-KJHZ003"],"award-info":[{"award-number":["2022-3-KJHZ003"]}]},{"name":"CCF-Ant Research Fund"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1109\/tpds.2025.3527649","type":"journal-article","created":{"date-parts":[[2025,1,8]],"date-time":"2025-01-08T20:35:19Z","timestamp":1736368519000},"page":"437-454","source":"Crossref","is-referenced-by-count":6,"title":["Chasing Common Knowledge: Joint Large Model Selection and Pulling in MEC With Parameter Sharing"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5350-3902","authenticated-orcid":false,"given":"Lizhen","family":"Zhou","sequence":"first","affiliation":[{"name":"DUT School of Software Technology & DUT-RU International School of Information Science and Engineering, Dalian, Liaoning, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5438-1468","authenticated-orcid":false,"given":"Zichuan","family":"Xu","sequence":"additional","affiliation":[{"name":"DUT School of Software Technology & DUT-RU International School of Information Science and Engineering, Dalian, Liaoning, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7978-4933","authenticated-orcid":false,"given":"Qiufen","family":"Xia","sequence":"additional","affiliation":[{"name":"DUT School of Software Technology & DUT-RU International School of Information Science and Engineering, Dalian, Liaoning, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6714-3185","authenticated-orcid":false,"given":"Zhou","family":"Xu","sequence":"additional","affiliation":[{"name":"DUT School of Software Technology & DUT-RU International School of Information Science and Engineering, Dalian, Liaoning, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8245-9189","authenticated-orcid":false,"given":"Wenhao","family":"Ren","sequence":"additional","affiliation":[{"name":"DUT School of Software Technology & DUT-RU International School of Information Science and Engineering, Dalian, Liaoning, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenbo","family":"Qi","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinjing","family":"Ma","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Song","family":"Yan","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuan","family":"Yang","sequence":"additional","affiliation":[{"name":"Alibaba Cloud, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"III-1220","article-title":"Thompson sampling for contextual bandits with linear payoffs","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Agrawal"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2362856"},{"key":"ref3","first-page":"41","article-title":"Multitask learning","volume-title":"Machine Learning","volume":"28","author":"Caruna","year":"1997"},{"key":"ref5","first-page":"613","article-title":"Clipper: A low-latency online prediction serving system","volume-title":"Proc. USENIX Conf. Netw. Syst. Des. Implementation","author":"Crankshaw"},{"key":"ref6","article-title":"A comprehensive survey of ai-generated content (AIGC): A history of generative AI from GAN to ChatGPT","author":"Cao","year":"2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3100298"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2022.3152493"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2021.3116665"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2014.2361138"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2023.3287547"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/S0377-2217(03)00274-1"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2021.3114193"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2011.111002"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2020.06.029"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/BF03006558"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737543"},{"key":"ref20","article-title":"Training compute-optimal large language models","author":"Hoffmann","year":"2022"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/tmc.2024.3415661"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2014.2338851"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/2398776.2398800"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/1815961.1815998"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_48"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/RTSS52674.2021.00034"},{"key":"ref27","first-page":"29","article-title":"Mainstream: Dynamic stem-sharing for multi-tenant video processing","volume-title":"Proc. USENIX Conf. Usenix Annu. Tech. Conf.","author":"Jiang"},{"key":"ref28","article-title":"Randomized rounding","author":"Kesselheim","year":"2018"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772758"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-03596-9_15"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2023.3236348"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.126"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2021.3125949"},{"key":"ref35","article-title":"Pushing large language models to the 6G Edge: Vision, challenges, and opportunities","author":"Lin","year":"2023"},{"key":"ref36","first-page":"611","article-title":"PRETZEL: Opening the black box of machine learning prediction serving systems","volume-title":"Proc. USENIX Conf. Operating Syst. Des. Implementation","author":"Lee"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3229556.3229562"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2946140"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3019805"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CCGridW59191.2023.00030"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CogMI48466.2019.00035"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2020.3006507"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3363143"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.433"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511813603"},{"key":"ref49","first-page":"973","article-title":"Gemel: Model merging for memory-efficient, real-time video analytics at the edge","volume-title":"Proc. USENIX Conf. Netw. Syst. Des. Implementation","author":"Padmanabhan"},{"key":"ref50","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Paszke"},{"key":"ref51","volume-title":"Combinatorial Optimization: Algorithms and Complexity","author":"Papadimitriou","year":"1998"},{"key":"ref52","first-page":"36","article-title":"TrimCaching: Parameter-sharing AI model caching in wireless edge networks","volume-title":"Proc. IEEE 44th Int. Conf. Distrib. Comput. Syst.","author":"Li"},{"issue":"68","key":"ref53","first-page":"1","article-title":"An information-theoretic analysis of thompson sampling","volume":"17","author":"Russo","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2022.3177569"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.jii.2020.100126"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3534088.3534352"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.5555\/3157096.3157329"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.3016344"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/comst.2024.3353265"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/LCN.2015.7366372"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2018.2877623"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2018.2881438"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM41043.2020.9155365"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/mvt.2023.3323757"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM54140.2023.10436771"},{"key":"ref67","article-title":"Cached model-as-a-resource: Provisioning large language model agents for edge intelligence in space-air-ground integrated networks","author":"Xu","year":"2024"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.204"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2021.3116597"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS57875.2023.00063"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2023.3250512"},{"key":"ref72","article-title":"Introduction to queueing theory and stochastic teletraffic models","author":"Zukerman","year":"2013"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/s13042-024-02443-6"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2022.3189186"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2023.3274647"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/71\/10850501\/10834568.pdf?arnumber=10834568","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,31]],"date-time":"2025-01-31T18:38:11Z","timestamp":1738348691000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10834568\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":67,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2025.3527649","relation":{},"ISSN":["1045-9219","1558-2183","2161-9883"],"issn-type":[{"value":"1045-9219","type":"print"},{"value":"1558-2183","type":"electronic"},{"value":"2161-9883","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3]]}}}