{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T15:45:30Z","timestamp":1782834330188,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":49,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"NSF","award":["2206522"],"award-info":[{"award-number":["2206522"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,9,10]]},"DOI":"10.1145\/3603269.3604830","type":"proceedings-article","created":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T16:16:29Z","timestamp":1693584989000},"page":"473-485","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":30,"title":["AdaInf: Data Drift Adaptive Scheduling for Accurate and SLO-guaranteed Multiple-Model Inference Serving at Edge Servers"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-9284-507X","authenticated-orcid":false,"given":"Sudipta Saha","family":"Shubha","sequence":"first","affiliation":[{"name":"Computer Science, University of Virginia, Charlottesville, Virginia, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7548-6223","authenticated-orcid":false,"given":"Haiying","family":"Shen","sequence":"additional","affiliation":[{"name":"Computer Science, University of Virginia, Charlottesville, Virginia, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,9]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Proc. of ATC","author":"Zhang Chengliang","year":"2019","unstructured":"Chengliang Zhang, Minchen Yu, Wei Wang, and Feng Yan. {MArk}: Exploiting cloud services for {Cost-Effective},{SLO-Aware} machine learning inference serving. In Proc. of ATC, 2019."},{"key":"e_1_3_2_1_2_1","volume-title":"Edge server. https:\/\/www.onlogic.com\/company\/io-hub\/what-are-edge-servers\/","author":"Fanton Darek","year":"2021","unstructured":"Darek Fanton. Edge server. https:\/\/www.onlogic.com\/company\/io-hub\/what-are-edge-servers\/, 2021."},{"key":"e_1_3_2_1_3_1","volume-title":"Proc. of NSDI","author":"Bhardwaj Romil","year":"2022","unstructured":"Romil Bhardwaj, Zhengxu Xia, Ganesh Ananthanarayanan, Junchen Jiang, Yuanchao Shu, Nikolaos Karianakis, Kevin Hsieh, Paramvir Bahl, and Ion Stoica. Ekya: Continuous learning of video analytics models on edge compute servers. In Proc. of NSDI, 2022."},{"key":"e_1_3_2_1_4_1","volume-title":"Proc. of SoCC","author":"Saurez Enrique","year":"2021","unstructured":"Enrique Saurez, Harshit Gupta, Alexandros Daglis, and Umakishore Ramachandran. Oneedge: An efficient control plane for geo-distributed infrastructures. In Proc. of SoCC, 2021."},{"key":"e_1_3_2_1_5_1","volume-title":"Proc. of SoCC","author":"Mittal Viyom","year":"2021","unstructured":"Viyom Mittal, Shixiong Qi, Ratnadeep Bhattacharya, Xiaosu Lyu, Junfeng Li, Sameer G Kulkarni, Dan Li, Jinho Hwang, KK Ramakrishnan, and Timothy Wood. Mu: an efficient, fair and responsive serverless framework for resource-constrained edge clouds. In Proc. of SoCC, 2021."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW54805.2022.00065"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781107298019"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.587"},{"key":"e_1_3_2_1_9_1","volume-title":"A continual learning survey: Defying forgetting in classification tasks","author":"Lange Matthias De","year":"2021","unstructured":"Matthias De Lange, Rahaf Aljundi, Marc Masana, Sarah Parisot, Xu Jia, Ale\u0161 Leonardis, Gregory Slabaugh, and Tinne Tuytelaars. A continual learning survey: Defying forgetting in classification tasks. IEEE transactions on pattern analysis and machine intelligence, 44(7), 2021."},{"key":"e_1_3_2_1_10_1","volume-title":"Proc. of SoCC","author":"Hu Yitao","year":"2021","unstructured":"Yitao Hu, Rajrup Ghosh, and Ramesh Govindan. Scrooge: A cost-effective deep learning inference system. In Proc. of SoCC, 2021."},{"key":"e_1_3_2_1_11_1","volume-title":"Proc. of SenSys","author":"Zeng Xiao","year":"2020","unstructured":"Xiao Zeng, Biyi Fang, Haichen Shen, and Mi Zhang. Distream: scaling live video analytics with workload-adaptive distributed edge intelligence. In Proc. of SenSys, 2020."},{"key":"e_1_3_2_1_12_1","volume-title":"Proc. of OSDI","author":"Bai Zhihao","year":"2020","unstructured":"Zhihao Bai, Zhen Zhang, Yibo Zhu, and Xin Jin. {PipeSwitch}: Fast pipelined context switching for deep learning applications. In Proc. of OSDI, 2020."},{"key":"e_1_3_2_1_13_1","volume-title":"Proc. of SC","author":"Rajbhandari Samyam","year":"2021","unstructured":"Samyam Rajbhandari, Olatunji Ruwase, Jeff Rasley, Shaden Smith, and Yuxiong He. Zero-infinity: Breaking the gpu memory wall for extreme scale deep learning. In Proc. of SC, 2021."},{"key":"e_1_3_2_1_14_1","volume-title":"Proc. of MLSys","author":"Wang Guanhua","year":"2021","unstructured":"Guanhua Wang, Kehan Wang, Kenan Jiang, Xiangjun Li, and Ion Stoica. Wavelet: Efficient dnn training with tick-tock scheduling. Proc. of MLSys, 2021."},{"key":"e_1_3_2_1_15_1","volume-title":"Proc. of ASPLOS","author":"Peng Xuan","year":"2020","unstructured":"Xuan Peng, Xuanhua Shi, Hulin Dai, Hai Jin, Weiliang Ma, Qian Xiong, Fan Yang, and Xuehai Qian. Capuchin: Tensor-based gpu memory management for deep learning. In Proc. of ASPLOS, 2020."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE53745.2022.00241"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/HiPC.2018.00024"},{"key":"e_1_3_2_1_18_1","volume-title":"Proc. of ATC","author":"Romero Francisco","year":"2021","unstructured":"Francisco Romero, Qian Li, Neeraja J Yadwadkar, and Christos Kozyrakis. {INFaaS}: Automated model-less inference serving. In Proc. of ATC, 2021."},{"key":"e_1_3_2_1_19_1","volume-title":"Twitter streaming traces. https:\/\/archive.org\/details\/archiveteam-twitter-stream-2018-04","year":"2018","unstructured":"Twitter. Twitter streaming traces. https:\/\/archive.org\/details\/archiveteam-twitter-stream-2018-04, 2018."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2004.1365067"},{"key":"e_1_3_2_1_21_1","volume-title":"Proc. of SoCC","author":"Daga Harshit","year":"2019","unstructured":"Harshit Daga, Patrick K Nicholson, Ada Gavrilovska, and Diego Lugones. Cartel: A system for collaborative transfer learning at the edge. In Proc. of SoCC, 2019."},{"key":"e_1_3_2_1_22_1","volume-title":"Proc. of MobiCom","author":"Laskaridis Stefanos","year":"2020","unstructured":"Stefanos Laskaridis, Stylianos I Venieris, Mario Almeida, Ilias Leontiadis, and Nicholas D Lane. Spinn: synergistic progressive inference of neural networks over device and cloud. In Proc. of MobiCom, 2020."},{"key":"e_1_3_2_1_23_1","volume-title":"Proc. of SOSP","author":"Shen Haichen","year":"2019","unstructured":"Haichen Shen, Lequn Chen, Yuchen Jin, Liangyu Zhao, Bingyu Kong, Matthai Philipose, Arvind Krishnamurthy, and Ravi Sundaram. Nexus: A gpu cluster engine for accelerating dnn-based video analysis. In Proc. of SOSP, 2019."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1039\/C3AY41907J"},{"key":"e_1_3_2_1_25_1","volume-title":"Proc. of OSDI","author":"Xiao Wencong","year":"2018","unstructured":"Wencong Xiao, Romil Bhardwaj, Ramachandran Ramjee, Muthian Sivathanu, Nipun Kwatra, Zhenhua Han, Pratyush Patel, Xuan Peng, Hanyu Zhao, Quanlu Zhang, et al. Gandiva: Introspective cluster scheduling for deep learning. In Proc. of OSDI, 2018."},{"key":"e_1_3_2_1_26_1","volume-title":"ICML","author":"Hendrycks Dan","year":"2019","unstructured":"Dan Hendrycks, Kimin Lee, and Mantas Mazeika. Using pre-training can improve model robustness and uncertainty. In ICML, 2019."},{"key":"e_1_3_2_1_27_1","volume-title":"Proc. of SoCC","author":"Crankshaw Daniel","year":"2020","unstructured":"Daniel Crankshaw, Gur-Eyal Sela, Xiangxi Mo, Corey Zumar, Ion Stoica, Joseph Gonzalez, and Alexey Tumanov. Inferline: latency-aware provisioning and scaling for prediction serving pipelines. In Proc. of SoCC, 2020."},{"key":"e_1_3_2_1_28_1","volume-title":"defense of the triplet loss for person re-identification. arXiv preprint arXiv:1703.07737","author":"Hermans Alexander","year":"2017","unstructured":"Alexander Hermans, Lucas Beyer, and Bastian Leibe. In defense of the triplet loss for person re-identification. arXiv preprint arXiv:1703.07737, 2017."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"e_1_3_2_1_30_1","volume-title":"Proc. of NSDI","author":"Zhang Haoyu","year":"2017","unstructured":"Haoyu Zhang, Ganesh Ananthanarayanan, Peter Bodik, Matthai Philipose, Paramvir Bahl, and Michael J Freedman. Live video analytics at scale with approximation and {Delay-Tolerance}. In Proc. of NSDI, 2017."},{"key":"e_1_3_2_1_31_1","volume-title":"Proc. of SenSys","author":"Liu Xiaochen","year":"2019","unstructured":"Xiaochen Liu, Pradipta Ghosh, Oytun Ulutan, BS Manjunath, Kevin Chan, and Ramesh Govindan. Caesar: cross-camera complex activity recognition. In Proc. of SenSys, 2019."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_33"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3450268.3453521"},{"key":"e_1_3_2_1_34_1","volume-title":"Deepspeed compression library. https:\/\/www.deepspeed.ai\/compression\/","year":"2023","unstructured":"DeepSpeed. Deepspeed compression library. https:\/\/www.deepspeed.ai\/compression\/, 2023."},{"key":"e_1_3_2_1_35_1","volume-title":"Nvidia multi-process service (mps). https:\/\/docs.nvidia.com\/deploy\/mps\/index.html","year":"2021","unstructured":"Nvidia. Nvidia multi-process service (mps). https:\/\/docs.nvidia.com\/deploy\/mps\/index.html, 2021."},{"key":"e_1_3_2_1_36_1","volume-title":"Nvidia profiling tool. https:\/\/developer.nvidia.com\/nvidia-system-management-interface","year":"2012","unstructured":"Nvidia. Nvidia profiling tool. https:\/\/developer.nvidia.com\/nvidia-system-management-interface, 2012."},{"key":"e_1_3_2_1_37_1","volume-title":"Proc. of NSDI","author":"Padmanabhan Arthi","year":"2023","unstructured":"Arthi Padmanabhan, Neil Agarwal, Anand Iyer, Ganesh Ananthanarayanan, Yuanchao Shu, Nikolaos Karianakis, Guoqing Harry Xu, and Ravi Netravali. Gemel: Model merging for memory-efficient, real-time video analytics at the edge. In Proc. of NSDI, 2023."},{"key":"e_1_3_2_1_38_1","volume-title":"Proc. of NSDI","author":"Zhang Hong","year":"2023","unstructured":"Hong Zhang, Yupeng Tang, Anurag Khandelwal, and Ion Stoica. {SHEPHERD}: Serving {DNNs} in the wild. In Proc. of NSDI, 2023."},{"key":"e_1_3_2_1_39_1","volume-title":"Proc. of OSDI","author":"Gujarati Arpan","year":"2020","unstructured":"Arpan Gujarati, Reza Karimi, Safya Alzayat, Wei Hao, Antoine Kaufmann, Ymir Vigfusson, and Jonathan Mace. Serving {DNNs} like clockwork: Performance predictability from the bottom up. In Proc. of OSDI, 2020."},{"key":"e_1_3_2_1_40_1","volume-title":"Proc. of NSDI","author":"Gunasekaran Jashwant Raj","year":"2022","unstructured":"Jashwant Raj Gunasekaran, Cyan Subhra Mishra, Prashanth Thinakaran, Bikash Sharma, Mahmut Taylan Kandemir, and Chita R Das. Cocktail: A multidimensional optimization for model serving in cloud. In Proc. of NSDI, 2022."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3489517.3530510"},{"key":"e_1_3_2_1_42_1","volume-title":"Proc. of SIGCOMM","author":"Jiang Junchen","year":"2018","unstructured":"Junchen Jiang, Ganesh Ananthanarayanan, Peter Bodik, Siddhartha Sen, and Ion Stoica. Chameleon: scalable adaptation of video analytics. In Proc. of SIGCOMM, 2018."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485730.3493446"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3304109.3306221"},{"key":"e_1_3_2_1_45_1","volume-title":"Proc. of EuroSys","author":"Kannan Ram Srivatsa","year":"2019","unstructured":"Ram Srivatsa Kannan, Lavanya Subramanian, Ashwin Raju, Jeongseob Ahn, Jason Mars, and Lingjia Tang. Grandslam: Guaranteeing slas for jobs in microservices execution frameworks. In Proc. of EuroSys, 2019."},{"key":"e_1_3_2_1_46_1","volume-title":"Proc. of NSDI","author":"Crankshaw Daniel","year":"2017","unstructured":"Daniel Crankshaw, Xin Wang, Guilio Zhou, Michael J Franklin, Joseph E Gonzalez, and Ion Stoica. Clipper: A {Low-Latency} online prediction serving system. In Proc. of NSDI, 2017."},{"key":"e_1_3_2_1_47_1","volume-title":"Proc. of ATC","author":"Choi Seungbeom","year":"2022","unstructured":"Seungbeom Choi, Sunho Lee, Yeonjae Kim, Jongse Park, Youngjin Kwon, and Jaehyuk Huh. Serving heterogeneous machine learning models on {Multi-GPU} servers with {Spatio-Temporal} sharing. In Proc. of ATC, 2022."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.2737\/FPL-GTR-290"},{"key":"e_1_3_2_1_49_1","volume-title":"Proc. of OSDI","author":"Han Mingcong","year":"2022","unstructured":"Mingcong Han, Hanze Zhang, Rong Chen, and Haibo Chen. Microsecond-scale preemption for concurrent {GPU-accelerated} {DNN} inferences. In Proc. of OSDI, 2022."}],"event":{"name":"ACM SIGCOMM '23: ACM SIGCOMM 2023 Conference","location":"New York NY USA","acronym":"ACM SIGCOMM '23","sponsor":["SIGCOMM ACM Special Interest Group on Data Communication"]},"container-title":["Proceedings of the ACM SIGCOMM 2023 Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3603269.3604830","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3603269.3604830","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3603269.3604830","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:46:41Z","timestamp":1750178801000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3603269.3604830"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9]]},"references-count":49,"alternative-id":["10.1145\/3603269.3604830","10.1145\/3603269"],"URL":"https:\/\/doi.org\/10.1145\/3603269.3604830","relation":{},"subject":[],"published":{"date-parts":[[2023,9]]},"assertion":[{"value":"2023-09-01","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}