{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,12]],"date-time":"2025-06-12T04:10:05Z","timestamp":1749701405788,"version":"3.41.0"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2025,6,11]],"date-time":"2025-06-11T00:00:00Z","timestamp":1749600000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,6,11]],"date-time":"2025-06-11T00:00:00Z","timestamp":1749600000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"DOI":"10.1007\/s11227-025-07508-z","type":"journal-article","created":{"date-parts":[[2025,6,11]],"date-time":"2025-06-11T14:43:20Z","timestamp":1749653000000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-user multi-exit DNN inference partitioning and task scheduling strategy"],"prefix":"10.1007","volume":"81","author":[{"given":"Xianzhong","family":"Tian","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yucheng","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuhua","family":"Mao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luoming","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziyi","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,6,11]]},"reference":[{"key":"7508_CR1","doi-asserted-by":"crossref","unstructured":"Zeiler MD, Fergus R (2014) Visualizing and understanding convolutional networks. In: Computer vision\u2014ECCV 2014, Cham, pp 818\u2013833","DOI":"10.1007\/978-3-319-10590-1_53"},{"issue":"10","key":"7508_CR2","doi-asserted-by":"publisher","first-page":"1533","DOI":"10.1109\/TASLP.2014.2339736","volume":"22","author":"O Abdel-Hamid","year":"2014","unstructured":"Abdel-Hamid O, Mohamed A-R, Jiang H, Deng L, Penn G, Yu D (2014) Convolutional neural networks for speech recognition. IEEE\/ACM Trans Audio Speech Lang Process 22(10):1533\u20131545","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"7508_CR3","unstructured":"Huval B, Wang T, Tandon S, Kiske J, Song W, Pazhayampallil J, Andriluka M, Rajpurkar P, Migimatsu T, Cheng-Yue R, Mujica F, Coates A, Ng AY (2015) An empirical evaluation of deep learning on highway driving. arXiv preprint arXiv:1504.01716"},{"key":"7508_CR4","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.media.2017.07.005","volume":"42","author":"G Litjens","year":"2017","unstructured":"Litjens G, Kooi T, Bejnordi BE, Setio AAA, Ciompi F, Ghafoorian M, van der Laak JAWM, van Ginneken B, S\u00e1nchez CI (2017) A survey on deep learning in medical image analysis. Med Image Anal 42:60\u201388","journal-title":"Med Image Anal"},{"key":"7508_CR5","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1016\/j.neucom.2023.02.006","volume":"531","author":"V Kamath","year":"2023","unstructured":"Kamath V, Renuka A (2023) Deep learning based object detection for resource constrained devices: systematic review, future trends and challenges ahead. Neurocomputing 531:34\u201360","journal-title":"Neurocomputing"},{"issue":"11","key":"7508_CR6","doi-asserted-by":"publisher","first-page":"2348","DOI":"10.1109\/TCAD.2018.2858384","volume":"37","author":"Z Zhao","year":"2018","unstructured":"Zhao Z, Barijough KM, Gerstlauer A (2018) Deepthings: distributed adaptive deep learning inference on resource-constrained iot edge clusters. IEEE Trans Comput Aided Des Integr Circuits Syst 37(11):2348\u20132359","journal-title":"IEEE Trans Comput Aided Des Integr Circuits Syst"},{"issue":"1","key":"7508_CR7","doi-asserted-by":"publisher","first-page":"615","DOI":"10.1145\/3093337.3037698","volume":"45","author":"Y Kang","year":"2017","unstructured":"Kang Y, Hauswald J, Gao C, Rovinski A, Mudge T, Mars J, Tang L (2017) Neurosurgeon: collaborative intelligence between the cloud and mobile edge. ACM SIGARCH Comput Archit News 45(1):615\u2013629","journal-title":"ACM SIGARCH Comput Archit News"},{"issue":"4","key":"7508_CR8","doi-asserted-by":"publisher","first-page":"2435","DOI":"10.1109\/TMC.2021.3114193","volume":"22","author":"M Gao","year":"2023","unstructured":"Gao M, Shen R, Shi L, Qi W, Li J, Li Y (2023) Task partitioning and offloading in dnn-task enabled mobile edge computing networks. IEEE Trans Mob Comput 22(4):2435\u20132445","journal-title":"IEEE Trans Mob Comput"},{"issue":"5","key":"7508_CR9","doi-asserted-by":"publisher","first-page":"3017","DOI":"10.1109\/TMC.2021.3125949","volume":"22","author":"J Li","year":"2023","unstructured":"Li J, Liang W, Li Y, Xu Z, Jia X, Guo S (2023) Throughput maximization of delay-aware dnn inference in edge computing by exploring dnn model partitioning and inference parallelism. IEEE Trans Mob Comput 22(5):3017\u20133030","journal-title":"IEEE Trans Mob Comput"},{"key":"7508_CR10","doi-asserted-by":"crossref","unstructured":"Teerapittayanon S, McDanel B, Kung HT (2016) Branchynet: fast inference via early exiting from deep neural networks. In: 2016 23rd International Conference on Pattern Recognition (ICPR), Cancun, Mexico, pp 2464\u20132469","DOI":"10.1109\/ICPR.2016.7900006"},{"key":"7508_CR11","doi-asserted-by":"crossref","unstructured":"Teerapittayanon S, McDanel B, Kung HT (2017) Distributed deep neural networks over the cloud, the edge and end devices. In: 2017 IEEE 37th International Conference on Distributed Computing Systems (ICDCS), Atlanta, GA, USA, pp 328\u2013339","DOI":"10.1109\/ICDCS.2017.226"},{"issue":"1","key":"7508_CR12","doi-asserted-by":"publisher","first-page":"535","DOI":"10.1109\/TMC.2022.3218724","volume":"23","author":"Z Liu","year":"2024","unstructured":"Liu Z, Song J, Qiu C, Wang X, Chen X, He Q, Sheng H (2024) Hastening stream offloading of inference via multi-exit dnns in mobile edge computing. IEEE Trans Mob Comput 23(1):535\u2013548","journal-title":"IEEE Trans Mob Comput"},{"issue":"9","key":"7508_CR13","first-page":"5389","volume":"22","author":"F Dong","year":"2023","unstructured":"Dong F, Wang H, Shen D, Huang Z, He Q, Zhang J, Wen L, Zhang T (2023) Multi-exit dnn inference acceleration based on multi-dimensional optimization for edge intelligence. IEEE Trans Mob Comput 22(9):5389\u20135405","journal-title":"IEEE Trans Mob Comput"},{"key":"7508_CR14","doi-asserted-by":"crossref","unstructured":"Fu Z, Ren J, Zhang D, Zhou Y, Zhang Y (2022) Kalmia: a heterogeneous qos-aware scheduling framework for dnn tasks on edge servers. In: IEEE INFOCOM 2022: IEEE Conference on Computer Communications, London, United Kingdom, pp 780\u2013789","DOI":"10.1109\/INFOCOM48880.2022.9796661"},{"key":"7508_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2023.110101","volume":"238","author":"I Al-hammadi","year":"2024","unstructured":"Al-hammadi I, Li M, Islam SMN, Al-Mosharea E (2024) Collaborative computation offloading for scheduling emergency tasks in sdn-based mobile edge computing networks. Comput Netw 238:110101","journal-title":"Comput Netw"},{"issue":"2","key":"7508_CR16","doi-asserted-by":"publisher","first-page":"534","DOI":"10.1109\/TCAD.2023.3314388","volume":"43","author":"W Liu","year":"2024","unstructured":"Liu W, Geng J, Zhu Z, Zhao Y, Ji C, Li C, Lian Z, Zhou X (2024) Ace-sniper: cloud\u2013edge collaborative scheduling framework with dnn inference latency modeling on heterogeneous devices. IEEE Trans Comput Aided Des Integr Circuits Syst 43(2):534\u2013547","journal-title":"IEEE Trans Comput Aided Des Integr Circuits Syst"},{"issue":"4","key":"7508_CR17","doi-asserted-by":"publisher","first-page":"3436","DOI":"10.1109\/TMC.2023.3276937","volume":"23","author":"Y Duan","year":"2024","unstructured":"Duan Y, Wu J (2024) Optimizing job offloading schedule for collaborative dnn inference. IEEE Trans Mob Comput 23(4):3436\u20133451","journal-title":"IEEE Trans Mob Comput"},{"issue":"1","key":"7508_CR18","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1109\/TPDS.2019.2931558","volume":"31","author":"Z Chen","year":"2020","unstructured":"Chen Z et al (2020) Deep learning research and development platform: characterizing and scheduling with qos guarantees on gpu clusters. IEEE Trans Parallel Distrib Syst 31(1):34\u201350","journal-title":"IEEE Trans Parallel Distrib Syst"},{"key":"7508_CR19","doi-asserted-by":"crossref","unstructured":"Pacheco RG, Shifrin M, Couto RS, Menasch\u00e9 DS, Hanawal MK, Campista MEM (2023) Adaee: adaptive early-exit dnn inference through multi-armed bandits. In: ICC 2023: IEEE International Conference on Communications, Rome, Italy, pp 3726\u20133731","DOI":"10.1109\/ICC45041.2023.10279243"},{"key":"7508_CR20","doi-asserted-by":"crossref","unstructured":"Huang J, Gao Y, Dong W (2023) Elastic dnn inference with unpredictable exit in edge computing. In: 2023 IEEE 43rd International Conference on Distributed Computing Systems (ICDCS), Hong Kong, pp 293\u2013304","DOI":"10.1109\/ICDCS57875.2023.00009"},{"key":"7508_CR21","doi-asserted-by":"crossref","unstructured":"Huang Z, Dong F, Shen D, Zhang J, Wang H, Cai G, He Q (2021) Enabling low latency edge intelligence based on multi-exit dnns in the wild. In: 2021 IEEE 41st International Conference on Distributed Computing Systems (ICDCS), pp 729\u2013739","DOI":"10.1109\/ICDCS51616.2021.00075"},{"key":"7508_CR22","doi-asserted-by":"crossref","unstructured":"Hou X, Liu J, Tang X, Li C, Cheng K-T, Li L, Guo M (2023) Mmexit: enabling fast and efficient multi-modal dnn inference with adaptive network exits. In: Euro-Par 2023: Parallel Processing: 29th International Conference on Parallel and Distributed Computing, Limassol, Cyprus, Berlin, Heidelberg, pp 426\u2013440","DOI":"10.1007\/978-3-031-39698-4_29"},{"issue":"10","key":"7508_CR23","doi-asserted-by":"publisher","first-page":"6041","DOI":"10.1109\/TMC.2022.3183098","volume":"22","author":"Z Hao","year":"2023","unstructured":"Hao Z, Xu G, Luo Y, Hu H, An J, Mao S (2023) Multi-agent collaborative inference via dnn decoupling: intermediate feature compression and edge learning. IEEE Trans Mob Comput 22(10):6041\u20136055","journal-title":"IEEE Trans Mob Comput"},{"issue":"6","key":"7508_CR24","doi-asserted-by":"publisher","first-page":"3260","DOI":"10.1109\/TSC.2021.3098816","volume":"15","author":"P Ren","year":"2022","unstructured":"Ren P, Qiao X, Huang Y, Liu L, Pu C, Dustdar S (2022) Fine-grained elastic partitioning for distributed dnn towards mobile web ar services in the 5g era. IEEE Trans Serv Comput 15(6):3260\u20133274","journal-title":"IEEE Trans Serv Comput"},{"issue":"1","key":"7508_CR25","doi-asserted-by":"publisher","first-page":"447","DOI":"10.1109\/TWC.2019.2946140","volume":"19","author":"E Li","year":"2020","unstructured":"Li E, Zeng L, Zhou Z, Chen X (2020) Edge ai: on-demand accelerating deep neural network inference via edge computing. IEEE Trans Wirel Commun 19(1):447\u2013457","journal-title":"IEEE Trans Wirel Commun"},{"key":"7508_CR26","doi-asserted-by":"crossref","unstructured":"Lim J-A, Kim Y (2022) Real-time dnn model partitioning for qoe enhancement in mobile vision applications. In: 2022 19th annual IEEE International Conference on Sensing, Communication, and Networking (SECON), pp 407\u2013415","DOI":"10.1109\/SECON55815.2022.9918600"},{"key":"7508_CR27","doi-asserted-by":"crossref","unstructured":"Sun B, Kloda T, Wu C, Caccamo M (2024) Partitioned scheduling and parallelism assignment for real-time dnn inference tasks on multi-tpu. In: Proceedings of the 61st ACM\/IEEE Design Automation Conference, New York, NY, USA, pp 1\u20136","DOI":"10.1145\/3649329.3655979"},{"key":"7508_CR28","doi-asserted-by":"crossref","unstructured":"Mohammed T, Joe-Wong C, Babbar R, Francesco MD (2020) Distributed inference acceleration with adaptive dnn partitioning and offloading. In: IEEE INFOCOM 2020: IEEE Conference on Computer Communications, Toronto, ON, Canada, pp 854\u2013863","DOI":"10.1109\/INFOCOM41043.2020.9155237"},{"key":"7508_CR29","volume-title":"Real-time systems","author":"JWSW Liu","year":"2000","unstructured":"Liu JWSW (2000) Real-time systems. Prentice Hall PTR, Hoboken"},{"issue":"1","key":"7508_CR30","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1145\/321738.321743","volume":"20","author":"CL Liu","year":"1973","unstructured":"Liu CL, Layland JW (1973) Scheduling algorithms for multiprogramming in a hard-real-time environment. J ACM 20(1):46\u201361","journal-title":"J ACM"},{"issue":"9","key":"7508_CR31","doi-asserted-by":"publisher","first-page":"5725","DOI":"10.1109\/TWC.2023.3235997","volume":"22","author":"W Liu","year":"2023","unstructured":"Liu W, Li B, Xie W, Dai Y, Fei Z (2023) Energy efficient computation offloading in aerial edge networks with multi-agent cooperation. IEEE Trans Wirel Commun 22(9):5725\u20135739","journal-title":"IEEE Trans Wirel Commun"},{"key":"7508_CR32","unstructured":"Schulman J, Wolski F, Dhariwal P, Radford A, Klimov O (2017) Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347"},{"issue":"12","key":"7508_CR33","first-page":"42","volume":"5","author":"M Akhtar","year":"2015","unstructured":"Akhtar M, Hamid B, Ur-Rehman I, Humayun M, Hamayun M, Khurshid H (2015) An optimized shortest job first scheduling algorithm for cpu scheduling. J Appl Environ Biol Sci 5(12):42\u201346","journal-title":"J Appl Environ Biol Sci"},{"key":"7508_CR34","volume-title":"Operating system concepts","author":"A Silberschatz","year":"2001","unstructured":"Silberschatz A, Gagne PG (2001) Operating system concepts, vol 6. Wiley, Hoboken"},{"issue":"3","key":"7508_CR35","first-page":"243","volume":"6","author":"S Mostafa Bozorgi","year":"2019","unstructured":"Mostafa Bozorgi S, Yazdani S (2019) Iwoa: an improved whale optimization algorithm for optimization problems. J Comput Des Eng 6(3):243\u2013259","journal-title":"J Comput Des Eng"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-025-07508-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-025-07508-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-025-07508-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,12]],"date-time":"2025-06-12T03:29:41Z","timestamp":1749698981000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-025-07508-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,11]]},"references-count":35,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2025,6]]}},"alternative-id":["7508"],"URL":"https:\/\/doi.org\/10.1007\/s11227-025-07508-z","relation":{},"ISSN":["1573-0484"],"issn-type":[{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,11]]},"assertion":[{"value":"26 May 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 June 2025","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"1014"}}