{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T17:08:09Z","timestamp":1781284089292,"version":"3.54.1"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"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":["62402226"],"award-info":[{"award-number":["62402226"]}],"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":["62172224"],"award-info":[{"award-number":["62172224"]}],"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":["62441225"],"award-info":[{"award-number":["62441225"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","award":["BK20241453"],"award-info":[{"award-number":["BK20241453"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","award":["BK20220138"],"award-info":[{"award-number":["BK20220138"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Central Universities","award":["30924010817"],"award-info":[{"award-number":["30924010817"]}]},{"name":"Central Universities","award":["30922010318"],"award-info":[{"award-number":["30922010318"]}]},{"name":"National Key Laboratory for Novel Software Technology","award":["KFKT2024B17"],"award-info":[{"award-number":["KFKT2024B17"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Mobile Comput."],"published-print":{"date-parts":[[2025,9]]},"DOI":"10.1109\/tmc.2025.3553201","type":"journal-article","created":{"date-parts":[[2025,3,21]],"date-time":"2025-03-21T15:33:36Z","timestamp":1742571216000},"page":"8089-8104","source":"Crossref","is-referenced-by-count":14,"title":["ExpertDRL: Request Dispatching and Instance Configuration for Serverless Edge Inference With Foundation Models"],"prefix":"10.1109","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5553-5534","authenticated-orcid":false,"given":"Yue","family":"Zeng","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7734-4077","authenticated-orcid":false,"given":"Junlong","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1065-449X","authenticated-orcid":false,"given":"Baoliu","family":"Ye","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7538-1985","authenticated-orcid":false,"given":"Zhihao","family":"Qu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Water Big Data Technology of Ministry of Water Resources, Hohai University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9831-2202","authenticated-orcid":false,"given":"Song","family":"Guo","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianjian","family":"Gong","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9057-5056","authenticated-orcid":false,"given":"Pan","family":"Li","sequence":"additional","affiliation":[{"name":"College of Electronic and Information Engineering, Southwest University, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Where to begin? On the impact of pre-training and initialization in federated learning","author":"Nguyen","year":"2022"},{"key":"ref2","first-page":"397","article-title":"INFaaS: Automated model-less inference serving","volume-title":"Proc. USENIX Annu. Techn. Conf.","author":"Romero"},{"key":"ref3","article-title":"Accelerating facebook\u2019s infrastructure with application-specific hardware","author":"Kevin","year":"2024"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.14778\/3547305.3547313"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00073"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507709"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2023.3329194"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2023.3281759"},{"key":"ref10","first-page":"613","article-title":"Clipper: A low-latency online prediction serving system","volume-title":"Proc. Symp. Netw. Syst. Des. Implementation","author":"Crankshaw"},{"key":"ref11","first-page":"1049","article-title":"MArk: Exploiting cloud services for cost-effective, SLO-Aware machine learning inference serving","volume-title":"Proc. USENIX Annu. Techn. Conf.","author":"Zhang"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/RTSS55097.2022.00032"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2022.3189186"},{"key":"ref14","article-title":"On the opportunities and risks of foundation models","author":"Bommasani","year":"2021"},{"key":"ref15","article-title":"On the importance and applicability of pre-training for federated learning","author":"Chen","year":"2022"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"key":"ref17","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Houlsby"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3230543.3230551"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3452296.3472902"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3511979"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2023.3240404"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.424"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018247"},{"key":"ref26","article-title":"AWSlambda pricing","year":"2024"},{"key":"ref27","article-title":"Pre-trained model accuracy","year":"2024"},{"key":"ref28","article-title":"OpenFaas","year":"2024"},{"key":"ref29","article-title":"Operating lambda: Performance optimization\u2013part 1","year":"2021"},{"key":"ref30","article-title":"Knapsack problem","year":"2024"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4613-0303-9_5"},{"key":"ref32","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lillicrap"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645333"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3581784.3613211"},{"key":"ref36","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Paszke"},{"key":"ref37","first-page":"995","article-title":"Beware of fragmentation: Scheduling GPU-Sharing workloads with fragmentation gradient descent","volume-title":"Proc. USENIX Annu. Techn. Conf.","author":"Weng"},{"key":"ref38","article-title":"Price autoDL","year":"2024"},{"key":"ref39","article-title":"Twitter streaming traces","year":"2018"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00045"},{"key":"ref41","article-title":"An image is worth 16 x\u200916 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref42","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"ref45","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017"},{"key":"ref46","volume-title":"Branch and Bound Methods","author":"Boyd","year":"2007"}],"container-title":["IEEE Transactions on Mobile Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7755\/11116789\/10935760.pdf?arnumber=10935760","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T04:54:26Z","timestamp":1754542466000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10935760\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9]]},"references-count":45,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tmc.2025.3553201","relation":{},"ISSN":["1536-1233","1558-0660","2161-9875"],"issn-type":[{"value":"1536-1233","type":"print"},{"value":"1558-0660","type":"electronic"},{"value":"2161-9875","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9]]}}}