{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T13:04:59Z","timestamp":1775912699587,"version":"3.50.1"},"reference-count":71,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"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":["62232004"],"award-info":[{"award-number":["62232004"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Jiangsu Provincial Frontier Technology Research and Development Program","award":["BF2024070"],"award-info":[{"award-number":["BF2024070"]}]},{"DOI":"10.13039\/501100013058","name":"Jiangsu Provincial Key Research and Development Program","doi-asserted-by":"publisher","award":["BE2022065-4"],"award-info":[{"award-number":["BE2022065-4"]}],"id":[{"id":"10.13039\/501100013058","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62272101"],"award-info":[{"award-number":["62272101"]}],"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":["62472094"],"award-info":[{"award-number":["62472094"]}],"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":["BK20230083"],"award-info":[{"award-number":["BK20230083"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Jiangsu Provincial Key Laboratory of Network and Information Security","award":["BM2003201"],"award-info":[{"award-number":["BM2003201"]}]},{"name":"Key Laboratory of Computer Network and Information Integration of Ministry of Education of China","award":["93K-9"],"award-info":[{"award-number":["93K-9"]}]},{"name":"Collaborative Innovation Center of Novel Software Technology and Industrialization"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Mobile Comput."],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1109\/tmc.2024.3514993","type":"journal-article","created":{"date-parts":[[2024,12,11]],"date-time":"2024-12-11T03:20:27Z","timestamp":1733887227000},"page":"3650-3666","source":"Crossref","is-referenced-by-count":9,"title":["Resource-Efficient DNN Inference With Early Exiting in Serverless Edge Computing"],"prefix":"10.1109","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9408-5647","authenticated-orcid":false,"given":"Xiaolin","family":"Guo","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Southeast University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6770-326X","authenticated-orcid":false,"given":"Fang","family":"Dong","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Southeast University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0422-5285","authenticated-orcid":false,"given":"Dian","family":"Shen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Southeast University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3941-6412","authenticated-orcid":false,"given":"Zhaowu","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Southeast University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9067-7896","authenticated-orcid":false,"given":"Jinghui","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Southeast University, Nanjing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2021.3054656"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE55515.2023.00030"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2022.3197669"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3578354.3592865"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3355118"},{"key":"ref6","article-title":"Cloud programming simplified: A Berkeley view on serverless computing","author":"Jonas","year":"2019"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM53939.2023.10229034"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796705"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651355"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640361"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672216"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2023.3262947"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3445814.3446714"},{"key":"ref14","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"ref15","article-title":"An analysis of deep neural network models for practical applications","author":"Canziani","year":"2016"},{"key":"ref16","first-page":"473","article-title":"Tetris: Memory-efficient serverless inference through tensor sharing","volume-title":"Proc. USENIX Annu. Tech. Conf.","author":"Li"},{"key":"ref17","article-title":"Azure functions","year":"2024"},{"key":"ref18","article-title":"Cloud Run functions","year":"2024"},{"key":"ref19","article-title":"AWS Lambda","year":"2024"},{"key":"ref20","article-title":"Open Source Serverless Cloud Platform","year":"2024"},{"key":"ref21","article-title":"AWS IoT Greengrass","year":"2024"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2023.3330849"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00073"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507709"},{"key":"ref25","first-page":"1049","article-title":"Mark: Exploiting cloud services for cost-effective, SLO-aware machine learning inference serving","volume-title":"Proc. USENIX Conf. Usenix Annu. Tech. Conf.","author":"Zhang"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01544"},{"key":"ref27","first-page":"16716","article-title":"Structural pruning for diffusion models","volume-title":"Proc. 37th Int. Conf. Neural Inf. Process. Syst.","author":"Fang"},{"key":"ref28","first-page":"42790","article-title":"A three-regime model of network pruning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhou"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2023.3242724"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2022.3172402"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2022.3218724"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2016.7900006"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3372224.3419194"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3545008.3545071"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2946140"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS51616.2021.00075"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/SEC.2018.00029"},{"key":"ref38","article-title":"The state of serverless","year":"2024"},{"key":"ref39","first-page":"133","article-title":"Peeking behind the curtains of serverless platforms","volume-title":"Proc. USENIX Conf. Usenix Annu. Tech. Conf.","author":"Wang"},{"key":"ref40","article-title":"GUROBI OPTIMIZER Gurobi 12.0","year":"2024"},{"key":"ref41","article-title":"Google OR-tools reference","year":"2024"},{"issue":"3","key":"ref42","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1007\/BF02591902","article-title":"On the average number of steps of the simplex method of linear programming","volume":"27","author":"Smale","year":"1983","journal-title":"Math. Program."},{"issue":"2","key":"ref43","first-page":"304","article-title":"Probability and computing: Randomized algorithms and probabilistic analysis","volume":"12","author":"Mitzenmacher","year":"2006","journal-title":"Bull. Symbolic Log."},{"key":"ref44","first-page":"1161","article-title":"Improving regret bounds for combinatorial semi-bandits with probabilistically triggered arms and its applications","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref45","first-page":"289","article-title":"Hermod: Principled and practical scheduling for serverless functions","volume-title":"Proc. 13th Symp. Cloud Comput.","author":"Kaffes"},{"key":"ref46","first-page":"205","article-title":"Serverless in the wild: Characterizing and optimizing the serverless workload at a large cloud provider","volume-title":"Proc. USENIX Conf. Usenix Annu. Tech. Conf.","author":"Shahrad"},{"key":"ref47","article-title":"Knative is an open-source enterprise-level solution to build serverless and event driven applications","year":"2024"},{"key":"ref48","article-title":"What is K3s?","year":"2024"},{"key":"ref49","article-title":"PyTorch get started","year":"2024"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref52","first-page":"649","article-title":"Character-level convolutional networks for text classification","volume-title":"Proc. 28th Int. Conf. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref53","article-title":"Ag\u2019s corpus of news articles","author":"Gulli","year":"2014"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref55","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Paszke"},{"key":"ref56","article-title":"NYS thruway origin and destination points for all vehicles","year":"2024"},{"key":"ref57","article-title":"Twitter trace on may 25th","year":"2024"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3620678.3624664"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3511990"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3581784.3613211"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645383"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/IWQoS61813.2024.10682915"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2024.3365134"},{"key":"ref64","first-page":"69","article-title":"Help rather than recycle: Alleviating cold startup in serverless computing through inter-function container sharing","volume-title":"Proc. USENIX Annu. Tech. Conf.","author":"Li"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.07.045"},{"key":"ref67","article-title":"A survey on methods and theories of quantized neural networks","author":"Guo","year":"2018"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/778"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547965"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2017.226"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611762"}],"container-title":["IEEE Transactions on Mobile Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7755\/10949650\/10787262.pdf?arnumber=10787262","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,7]],"date-time":"2025-04-07T22:15:33Z","timestamp":1744064133000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10787262\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5]]},"references-count":71,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tmc.2024.3514993","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":[[2025,5]]}}}