{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T15:14:22Z","timestamp":1783523662824,"version":"3.55.0"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"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. Comput. Sci. Technol."],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1007\/s11390-025-5623-5","type":"journal-article","created":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T14:22:02Z","timestamp":1783520522000},"page":"494-505","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Duba: Cost-Efficient Serverless Cloud-Edge Collaborative Machine Learning Serving with Dual-Batching"],"prefix":"10.1007","volume":"41","author":[{"given":"Jian-Xiong","family":"Liao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Peng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhi","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fei","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,8]]},"reference":[{"issue":"8","key":"5623_CR1","doi-asserted-by":"publisher","first-page":"1738","DOI":"10.1109\/JPROC.2019.2918951","volume":"107","author":"Z Zhou","year":"2019","unstructured":"Zhou Z, Chen X, Li E, Zeng L, Luo K, Zhang J. Edge intelligence: Paving the last mile of artificial intelligence with edge computing. Proceedings of the IEEE, 2019, 107(8): 1738\u20131762. DOI: https:\/\/doi.org\/10.1109\/JPROC.2019.2918951.","journal-title":"Proceedings of the IEEE"},{"key":"5623_CR2","doi-asserted-by":"publisher","unstructured":"Bourechak A, Zedadra O, Kouahla M N, Guerrieri A, Seridi H, Fortino G. At the confluence of artificial intelligence and edge computing in IoT-based applications: A review and new perspectives. Sensors, 2023, 23(3): Article No. 1639. DOI: https:\/\/doi.org\/10.3390\/S23031639.","DOI":"10.3390\/S23031639"},{"key":"5623_CR3","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00073","volume-title":"Proc. the International Conference for High Performance Computing, Networking, Storage and Analysis","author":"A Ali","year":"2020","unstructured":"Ali A, Pinciroli R, Yan F, Smirni E. BATCH: Machine learning inference serving on serverless platforms with adaptive batching. In Proc. the International Conference for High Performance Computing, Networking, Storage and Analysis, Nov. 2020. DOI: https:\/\/doi.org\/10.1109\/SC41405.2020.00073."},{"key":"5623_CR4","doi-asserted-by":"publisher","DOI":"10.1109\/VTC2024-SPRING62846.2024.10682995","volume-title":"Proc. the 99th IEEE Vehicular Technology Conference","author":"Y She","year":"2024","unstructured":"She Y, Shi T, Wang J, Liu B. Dynamic batching and early-exiting for accurate and timely edge inference. In Proc. the 99th IEEE Vehicular Technology Conference, Jun. 2024. DOI: https:\/\/doi.org\/10.1109\/VTC2024-SPRING62846.2024.10682995."},{"issue":"10","key":"5623_CR5","doi-asserted-by":"publisher","first-page":"13782","DOI":"10.1109\/TWC.2024.3404811","volume":"23","author":"Y Cang","year":"2024","unstructured":"Cang Y, Chen M, Huang K. Joint batching and scheduling for high-throughput multiuser edge AI with asynchronous task arrivals. IEEE Trans. Wireless Communications, 2024, 23(10): 13782\u201313795. DOI: https:\/\/doi.org\/10.1109\/TWC.2024.3404811.","journal-title":"IEEE Trans. Wireless Communications"},{"key":"5623_CR6","doi-asserted-by":"publisher","first-page":"263","DOI":"10.1145\/3267809.3267815","volume-title":"Proc. the ACM Symposium on Cloud Computing","author":"L Ao","year":"2018","unstructured":"Ao L, Izhikevich L, Voelker G M, Porter G. Sprocket: A serverless video processing framework. In Proc. the ACM Symposium on Cloud Computing, Oct. 2018, pp.263\u2013274. DOI: https:\/\/doi.org\/10.1145\/3267809.3267815."},{"key":"5623_CR7","doi-asserted-by":"publisher","first-page":"4171","DOI":"10.18653\/V1\/N19-1423","volume-title":"Proc. the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"J Devlin","year":"2019","unstructured":"Devlin J, Chang M W, Lee K, Toutanova K. BERT: Pretraining of deep bidirectional transformers for language understanding. In Proc. the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Jun. 2019, pp.4171\u20134186. DOI: https:\/\/doi.org\/10.18653\/V1\/N19-1423."},{"key":"5623_CR8","first-page":"193","volume-title":"Proc. the 18th USENIX Symposium on Operating Systems Design and Implementation","author":"Y Zhong","year":"2024","unstructured":"Zhong Y, Liu S, Chen J, Hu J, Zhu Y, Liu X, Jin X, Zhang H. Distserve: Disaggregating prefill and decoding for goodput-optimized large language model serving. In Proc. the 18th USENIX Symposium on Operating Systems Design and Implementation, Jul. 2024, pp.193\u2013210."},{"key":"5623_CR9","doi-asserted-by":"publisher","DOI":"10.1009\/HPEC49654.2021.9622863","volume-title":"Proc. the 2021 IEEE High Performance Extreme Computing Conference","author":"B Li","year":"2021","unstructured":"Li B, Gadepally V, Samsi S, Veillette M, Tiwari D. Serving machine learning inference using heterogeneous hardware. In Proc. the 2021 IEEE High Performance Extreme Computing Conference, Sept. 2021. DOI: https:\/\/doi.org\/10.1009\/HPEC49654.2021.9622863."},{"key":"5623_CR10","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1145\/3552326.3587459","volume-title":"Proc. the 18th European Conference on Computer Systems","author":"M Park","year":"2023","unstructured":"Park M, Bhardwaj K, Gavrilovska A. Pocket: ML serving from the edge. In Proc. the 18th European Conference on Computer Systems, May 2023, pp.46\u201362. DOI: https:\/\/doi.org\/10.1145\/3552326.3587459."},{"key":"5623_CR11","doi-asserted-by":"publisher","unstructured":"Murshed M G S, Murphy C, Hou D, Khan N, Ananthanarayanan G, Hussain F. Machine learning at the network edge: A survey. ACM Computing Surveys (CSUR), 2022, 54(8): Article No. 170. DOI: https:\/\/doi.org\/10.1145\/3469029.","DOI":"10.1145\/3469029"},{"key":"5623_CR12","doi-asserted-by":"publisher","first-page":"372","DOI":"10.1109\/ICDCS57875.2023.00040","volume-title":"Proc. the 43rd IEEE International Conference on Distributed Computing Systems","author":"Z Wu","year":"2023","unstructured":"Wu Z, Deng Y, Zhou Y, Li J, Pang S. FaaSBatch: Enhancing the efficiency of serverless computing by batching and expanding functions. In Proc. the 43rd IEEE International Conference on Distributed Computing Systems, Jul. 2023, pp.372\u2013382. DOI: https:\/\/doi.org\/10.1109\/ICDCS57875.2023.00040."},{"key":"5623_CR13","doi-asserted-by":"publisher","first-page":"366","DOI":"10.1109\/RTSS46320.2019.00040","volume-title":"Proc. the 2019 IEEE Real-Time Systems Symposium","author":"D Zhang","year":"2019","unstructured":"Zhang D, Vance N, Zhang Y, Rashid T, Wang D. Edge-Batch: Towards AI-empowered optimal task batching in intelligent edge systems. In Proc. the 2019 IEEE Real-Time Systems Symposium, Dec. 2019, pp.366\u2013379. DOI: https:\/\/doi.org\/10.1109\/RTSS46320.2019.00040."},{"key":"5623_CR14","doi-asserted-by":"publisher","first-page":"2261","DOI":"10.1109\/CVPR.2017.243","volume-title":"Proc. the 2017 IEEE Conference on Computer Vision and Pattern Recognition","author":"G Huang","year":"2017","unstructured":"Huang G, Liu Z, Van Der Maaten L, Weinberger K Q. Densely connected convolutional networks. In Proc. the 2017 IEEE Conference on Computer Vision and Pattern Recognition, Jul. 2017, pp.2261\u20132269. DOI: https:\/\/doi.org\/10.1109\/CVPR.2017.243."},{"key":"5623_CR15","doi-asserted-by":"publisher","first-page":"2818","DOI":"10.1109\/CVPR.2016.308","volume-title":"Proc. the 2016 IEEE Conference on Computer Vision and Pattern Recognition","author":"C Szegedy","year":"2016","unstructured":"Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z. Rethinking the inception architecture for computer vision. In Proc. the 2016 IEEE Conference on Computer Vision and Pattern Recognition, Jun. 2016, pp.2818\u20132826. DOI: https:\/\/doi.org\/10.1109\/CVPR.2016.308."},{"key":"5623_CR16","doi-asserted-by":"publisher","first-page":"4510","DOI":"10.1109\/CVPR.2018.00474","volume-title":"Proc. the 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"M Sandler","year":"2018","unstructured":"Sandler M, Howard A, Zhu M, Zhmoginov A, Chen L C. Mobilenetv2: Inverted residuals and linear bottlenecks. In Proc. the 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Jun. 2018, pp.4510\u20134520. DOI: https:\/\/doi.org\/10.1109\/CVPR.2018.00474."},{"key":"5623_CR17","doi-asserted-by":"publisher","first-page":"770","DOI":"10.1109\/CVPR.2016.90","volume-title":"Proc. the 2016 IEEE Conference on Computer Vision and Pattern Recognition","author":"K He","year":"2016","unstructured":"He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In Proc. the 2016 IEEE Conference on Computer Vision and Pattern Recognition, Jun. 2016, pp.770\u2013778. DOI: https:\/\/doi.org\/10.1109\/CVPR.2016.90."},{"issue":"10","key":"5623_CR18","doi-asserted-by":"publisher","first-page":"2071","DOI":"10.14778\/3547305.3547313","volume":"15","author":"A Ali","year":"2022","unstructured":"Ali A, Pinciroli R, Yan F, Smirni E. Optimizing inference serving on serverless platforms. Proceedings of the VLDB Endowment, 2022, 15(10): 2071\u20132084. DOI: https:\/\/doi.org\/10.14778\/3547305.3547313.","journal-title":"Proceedings of the VLDB Endowment"},{"key":"5623_CR19","doi-asserted-by":"publisher","first-page":"753","DOI":"10.1145\/3503222.3507750","volume-title":"Proc. the 27th ACM International Conference on Architectural Support for Programming Languages and Operating Systems","author":"R B Roy","year":"2022","unstructured":"Roy R B, Patel T, Tiwari D. IceBreaker: Warming server-less functions better with heterogeneity. In Proc. the 27th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Feb. 2022, pp.753\u2013767. DOI: https:\/\/doi.org\/10.1145\/3503222.3507750."},{"key":"5623_CR20","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1145\/3617232.3624871","volume-title":"Proc. the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems","author":"H Yu","year":"2024","unstructured":"Yu H, Roy R B, Fontenot C, Tiwari D, Li J, Zhang H, Wang H, Park S J. RainbowCake: Mitigating cold-starts in serverless with layer-wise container caching and sharing. In Proc. the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Apr. 27\u2013May 1, 2024, pp.335\u2013350. DOI: https:\/\/doi.org\/10.1145\/3617232.3624871."},{"key":"5623_CR21","doi-asserted-by":"crossref","unstructured":"Zhang Z, Li H, Zhao Y, Lin C, Liu J. BCEdge: SLO-aware DNN inference services with adaptive batching on edge platforms. arXiv: 2305.01519, 2023. https:\/\/arxiv.org\/abs\/2305.01519, Mar. 2026.","DOI":"10.36227\/techrxiv.22724099"},{"issue":"3","key":"5623_CR22","doi-asserted-by":"publisher","first-page":"1489","DOI":"10.1109\/TCC.2020.2997008","volume":"10","author":"C Ding","year":"2022","unstructured":"Ding C, Zhou A, Liu Y, Chang R N, Hsu C H, Wang S. A cloud-edge collaboration framework for cognitive service. IEEE Trans. Cloud Computing, 2022, 10(3): 1489\u20131499. DOI: https:\/\/doi.org\/10.1109\/TCC.2020.2997008.","journal-title":"IEEE Trans. Cloud Computing"},{"key":"5623_CR23","doi-asserted-by":"publisher","unstructured":"Qi H, Ren F, Wang L, Jiang P, Wan S, Deng X. Multi-compression scale DNN inference acceleration based on cloud-edge-end collaboration. ACM Trans. Embedded Computing Systems, 2024, 23(1): Article No. 16. DOI: https:\/\/doi.org\/10.1145\/3634704.","DOI":"10.1145\/3634704"},{"key":"5623_CR24","doi-asserted-by":"publisher","DOI":"10.1109\/IPCCC51483.2021.9679434","volume-title":"Proc. the 2021 IEEE International Performance, Computing, and Communications Conference","author":"J Chen","year":"2021","unstructured":"Chen J, Qi Q, Wang J, Sun H, Liao J. Accelerating DNN inference by edge-cloud collaboration. In Proc. the 2021 IEEE International Performance, Computing, and Communications Conference, Oct. 2021. DOI: https:\/\/doi.org\/10.1109\/IPCCC51483.2021.9679434."},{"key":"5623_CR25","doi-asserted-by":"publisher","first-page":"409","DOI":"10.1109\/DAC18074.2021.9586176","volume-title":"Proc. the 58th ACM\/IEEE Design Automation Conference","author":"M Li","year":"2021","unstructured":"Li M, Li Y, Tian Y, Jiang L, Xu Q. Appealnet: An efficient and highly-accurate edge\/cloud collaborative architecture for DNN inference. In Proc. the 58th ACM\/IEEE Design Automation Conference, Dec. 2021, pp.409\u2013414. DOI: https:\/\/doi.org\/10.1109\/DAC18074.2021.9586176."},{"key":"5623_CR26","doi-asserted-by":"publisher","first-page":"316","DOI":"10.1109\/ICWS67624.2025.00046","volume-title":"Proc. the 2025 IEEE International Conference on Web Services","author":"H Jin","year":"2025","unstructured":"Jin H, Wu Y. CE-CoLLM: Efficient and adaptive large language models through cloud-edge collaboration. In Proc. the 2025 IEEE International Conference on Web Services, Jul. 2025, pp.316\u2013323. DOI: https:\/\/doi.org\/10.1109\/ICWS67624.2025.00046."},{"key":"5623_CR27","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1109\/IC2E61754.2024.00014","volume-title":"Proc. the 2024 IEEE International Conference on Cloud Engineering","author":"M Malekabbasi","year":"2024","unstructured":"Malekabbasi M, Pfandzelter T, Schirmer T, Bermbach D. GeoFaaS: An edge-to-cloud FaaS platform. In Proc. the 2024 IEEE International Conference on Cloud Engineering, Sept. 2024, pp.66\u201371. DOI: https:\/\/doi.org\/10.1109\/IC2E61754.2024.00014."},{"issue":"8","key":"5623_CR28","doi-asserted-by":"publisher","first-page":"8111","DOI":"10.1109\/TMC.2023.3348165","volume":"23","author":"K Zhao","year":"2024","unstructured":"Zhao K, Zhou Z, Jiao L, Cai S, Xu F, Chen X. Taming serverless cold start of cloud model inference with edge computing. IEEE Trans. Mobile Computing, 2024, 23(8): 8111\u20138128. DOI: https:\/\/doi.org\/10.1109\/TMC.2023.3348165.","journal-title":"IEEE Trans. Mobile Computing"},{"key":"5623_CR29","doi-asserted-by":"publisher","first-page":"768","DOI":"10.1145\/3503222.3507709","volume-title":"Proc. the 27th ACM International Conference on Architectural Support for Programming Languages and Operating Systems","author":"Y Yang","year":"2022","unstructured":"Yang Y, Zhao L, Li Y, Zhang H, Li J, Zhao M, Chen X, Li K. INFless: A native serverless system for low-latency, high-throughput inference. In Proc. the 27th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Feb. 28\u2013Mar. 4, 2022, pp.768\u2013781. DOI: https:\/\/doi.org\/10.1145\/3503222.3507709."},{"key":"5623_CR30","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1145\/3609510.3609816","volume-title":"Proc. the 14th ACM SIGOPS Asia-Pacific Workshop on Systems","author":"S Cai","year":"2023","unstructured":"Cai S, Zhou Z, Zhao K, Chen X. Cost-efficient serverless inference serving with joint batching and multi-processing. In Proc. the 14th ACM SIGOPS Asia-Pacific Workshop on Systems, Aug. 2023, pp.43\u201349. DOI: https:\/\/doi.org\/10.1145\/3609510.3609816."}],"container-title":["Journal of Computer Science and Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11390-025-5623-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11390-025-5623-5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11390-025-5623-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T14:22:03Z","timestamp":1783520523000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11390-025-5623-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":30,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,3]]}},"alternative-id":["5623"],"URL":"https:\/\/doi.org\/10.1007\/s11390-025-5623-5","relation":{},"ISSN":["1000-9000","1860-4749"],"issn-type":[{"value":"1000-9000","type":"print"},{"value":"1860-4749","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]},"assertion":[{"value":"31 May 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 September 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 July 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Conflict of Interest\n                      The authors declare that they have no conflict of interest.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics"}}]}}