{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T01:53:14Z","timestamp":1773193994457,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":58,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,6,10]],"date-time":"2022-06-10T00:00:00Z","timestamp":1654819200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072033"],"award-info":[{"award-number":["62072033"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Singapore University of Technology and Design's startup grant","award":["SRG-ISTD-2009-144"],"award-info":[{"award-number":["SRG-ISTD-2009-144"]}]},{"name":"Singapore Ministry of Education Academic Research Fund Tier 3","award":["MOE2017-T3-1-007"],"award-info":[{"award-number":["MOE2017-T3-1-007"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,6,10]]},"DOI":"10.1145\/3514221.3517905","type":"proceedings-article","created":{"date-parts":[[2022,6,12]],"date-time":"2022-06-12T02:33:49Z","timestamp":1655001229000},"page":"1866-1875","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":23,"title":["Serverless Data Science - Are We There Yet? A Case Study of Model Serving"],"prefix":"10.1145","author":[{"given":"Yuncheng","family":"Wu","sequence":"first","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}]},{"given":"Tien Tuan Anh","family":"Dinh","sequence":"additional","affiliation":[{"name":"Singapore University of Technology and Design, Singapore, Singapore"}]},{"given":"Guoyu","family":"Hu","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}]},{"given":"Meihui","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology, Beijing, China"}]},{"given":"Yeow Meng","family":"Chee","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}]},{"given":"Beng Chin","family":"Ooi","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}]}],"member":"320","published-online":{"date-parts":[[2022,6,11]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"[n.d.]. Regulation (eu) 2016\/679 of the european parliament and of the council of 27 april 2016 on the protection of natural persons with regard to the processing of personal data and on the free movement of such data and repealing directive 95\/46\/ec (general data protection regulation). OJ 2016-04--27. ([n. d.])."},{"key":"e_1_3_2_2_2_1","volume-title":"BATCH: Machine Learning Inference Serving on Serverless Platforms with Adaptive Batching. In SC. 972--986.","author":"Ali A.","year":"2020","unstructured":"A. Ali, R. Pinciroli, F. Yan, and E. Smirni. 2020. BATCH: Machine Learning Inference Serving on Serverless Platforms with Adaptive Batching. In SC. 972--986."},{"key":"e_1_3_2_2_3_1","unstructured":"Amazon. 2021. Amazon Web Services. https:\/\/aws.amazon.com\/."},{"key":"e_1_3_2_2_4_1","first-page":"2021","article-title":"AWS EC2. https:\/\/aws.amazon.com\/ec2\/","year":"2021","unstructured":"Amazon. 2021. AWS EC2. https:\/\/aws.amazon.com\/ec2\/. Accessed: 2021-06.","journal-title":"Accessed"},{"key":"e_1_3_2_2_5_1","unstructured":"Amazon. 2021. AWS Lambda Quotas. https:\/\/docs.aws.amazon.com\/lambda\/latest\/dg\/gettingstarted-limits.html. Accessed: 2021--10."},{"key":"e_1_3_2_2_6_1","unstructured":"Amazon. 2021. AWS Lambda. https:\/\/aws.amazon.com\/lambda\/. Accessed: 2021--10."},{"key":"e_1_3_2_2_7_1","first-page":"2021","article-title":"AWS SageMaker. https:\/\/aws.amazon.com\/sagemaker\/","year":"2021","unstructured":"Amazon. 2021. AWS SageMaker. https:\/\/aws.amazon.com\/sagemaker\/. Accessed: 2021-06.","journal-title":"Accessed"},{"key":"e_1_3_2_2_8_1","unstructured":"CalorieKing. 2021. CalorieKing. https:\/\/www.calorieking.com\/us\/en\/foods\/."},{"key":"e_1_3_2_2_9_1","volume-title":"Katz","author":"Carreira Joao","year":"2019","unstructured":"Joao Carreira, Pedro Fonseca, Alexey Tumanov, Andrew Zhang, and Randy H. Katz. 2019. Cirrus: a Serverless Framework for End-to-end ML Workflows. In SoCC. 13--24."},{"key":"e_1_3_2_2_10_1","unstructured":"Alex Casalboni. 2021. AWS Lambda Power Tuning. https:\/\/github.com\/alexcasalboni\/aws-lambda-power-tuning."},{"key":"e_1_3_2_2_11_1","unstructured":"Marcin Copik Grzegorz Kwasniewski Maciej Besta Michal Podstawski and Torsten Hoefler. 2021. SeBS: A Serverless Benchmark Suite for Function-as-a- Service Computing. In Middleware."},{"key":"e_1_3_2_2_12_1","volume-title":"Clipper: A Low-Latency Online Prediction Serving System. In NSDI. 613--627.","author":"Crankshaw Daniel","year":"2017","unstructured":"Daniel Crankshaw, Xin Wang, Guilio Zhou, Michael J. Franklin, Joseph E. Gonzalez, and Ion Stoica. 2017. Clipper: A Low-Latency Online Prediction Serving System. In NSDI. 613--627."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"crossref","unstructured":"Vojislav Dukic Rodrigo Bruno Ankit Singla and Gustavo Alonso. 2020. Photons: lambdas on a diet. In SoCC. 45--59.","DOI":"10.1145\/3419111.3421297"},{"key":"e_1_3_2_2_14_1","volume-title":"Dilma Da Silva, and Jiang Hu","author":"Feng Lang","year":"2018","unstructured":"Lang Feng, Prabhakar Kudva, Dilma Da Silva, and Jiang Hu. 2018. Exploring Serverless Computing for Neural Network Training. In CLOUD. 334--341."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/0166-5316(93)90035-S"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"crossref","unstructured":"Alexander Fuerst and Prateek Sharma. 2021. FaasCache: keeping serverless computing alive with greedy-dual caching. In ASPLOS. 386--400.","DOI":"10.1145\/3410276"},{"key":"e_1_3_2_2_17_1","first-page":"2021","article-title":"Google AI Platform. https:\/\/cloud.google.com\/ai-platform","year":"2021","unstructured":"Google. 2021. Google AI Platform. https:\/\/cloud.google.com\/ai-platform. Accessed: 2021-06.","journal-title":"Accessed"},{"key":"e_1_3_2_2_18_1","unstructured":"Google. 2021. Google Cloud Functions. https:\/\/cloud.google.com\/functions. Accessed: 2021--10."},{"key":"e_1_3_2_2_19_1","unstructured":"Google. 2021. Google Cloud. https:\/\/cloud.google.com\/."},{"key":"e_1_3_2_2_20_1","first-page":"2021","article-title":"Google Compute Engine. https:\/\/cloud.google.com\/compute","year":"2021","unstructured":"Google. 2021. Google Compute Engine. https:\/\/cloud.google.com\/compute. Accessed: 2021-06.","journal-title":"Accessed"},{"key":"e_1_3_2_2_21_1","unstructured":"Google. 2021. TensorFlow Saved Model. https:\/\/www.tensorflow.org\/tfx\/serving\/saved_model_warmup."},{"key":"e_1_3_2_2_22_1","unstructured":"Google. 2021. TensorFlow. https:\/\/www.tensorflow.org\/."},{"key":"e_1_3_2_2_23_1","volume-title":"Brandenburg","author":"Gujarati Arpan","year":"2017","unstructured":"Arpan Gujarati, Sameh Elnikety, Yuxiong He, Kathryn S. McKinley, and Bj\u00f6rn B. Brandenburg. 2017. Swayam: Distributed Autoscaling to Meet SLAs of Machine Learning Inference Services with Resource Efficiency. In Middleware. 109--120."},{"key":"e_1_3_2_2_24_1","unstructured":"Arpan Gujarati Reza Karimi Safya Alzayat Wei Hao Antoine Kaufmann Ymir Vigfusson and Jonathan Mace. 2020. Serving DNNs like Clockwork: Performance Predictability from the Bottom Up. In OSDI. 443--462."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"crossref","unstructured":"Kim Hazelwood Sarah Bird David Brooks Soumith Chintala Utku Diril Dmytro Dzhulgakov Mohamed Fawzy Bill Jia Yangqing Jia Aditya Kalro James Law Kevin Lee Jason Lu Pieter Noordhuis Misha Smelyanskiy Liang Xiong and Xiaodong Wang. 2018. Applied Machine Learning at Facebook: A Datacenter Infrastructure Perspective. In HPCA.","DOI":"10.1109\/HPCA.2018.00059"},{"key":"e_1_3_2_2_26_1","volume-title":"Serverless Computing: One Step Forward, Two Steps Back. In CIDR.","author":"Hellerstein Joseph M.","year":"2019","unstructured":"Joseph M. Hellerstein, Jose Faleiro, Joseph E. Gonzalez, Johann Schleier-Smith, Vikram Sreekanti, Alexey Tumanov, and Chenggang Wu. 2019. Serverless Computing: One Step Forward, Two Steps Back. In CIDR."},{"key":"e_1_3_2_2_27_1","volume-title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. CoRR abs\/1704.04861","author":"Howard Andrew G.","year":"2017","unstructured":"Andrew G. Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, and Hartwig Adam. 2017. MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. CoRR abs\/1704.04861 (2017)."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"crossref","unstructured":"Junchen Jiang Ganesh Ananthanarayanan Peter Bodik Siddhartha Sen and Ion Stoica. 2018. Chameleon: scalable adaption of video analytics. In SIGCOMM.","DOI":"10.1145\/3230543.3230574"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"crossref","unstructured":"Jiawei Jiang Shaoduo Gan Yue Liu Fanlin Wang Gustavo Alonso Ana Klimovic Ankit Singla Wentao Wu and Ce Zhang. 2021. Towards Demystifying Serverless Machine Learning Training. In SIGMOD. 857--871.","DOI":"10.1145\/3448016.3459240"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"crossref","unstructured":"Eric Jonas Qifan Pu Shivaram Venkataraman Ion Stoica and Benjamin Recht. 2017. Occupy the cloud: Distributed computing for the 99%. In SoCC. 445--451.","DOI":"10.1145\/3127479.3128601"},{"key":"e_1_3_2_2_31_1","volume-title":"Ion Stoica, and David A. Patterson.","author":"Jonas Eric","year":"2019","unstructured":"Eric Jonas, Johann Schleier-Smith, Vikram Sreekanti, Chia-Che Tsai, Anurag Khandelwal, Qifan Pu, Vaishaal Shankar, Joao Carreira, Karl Krauth, Neeraja Yadwadkar, Joseph E. Gonzalez, Raluca Ada Popa, Ion Stoica, and David A. Patterson. 2019. Cloud Programming Simplified: A Berkeley View on Serverless Computing. Technical Report. UC Berkeley."},{"key":"e_1_3_2_2_32_1","unstructured":"Ana Klimovic Yawen Wang Christos Kozyrakis Patrick Stuedi Jonas Pfefferle and Animesh Trivedi. 2018. Understanding ephemeral storage for serverless analytics. In Usenix ATC. 789--794."},{"key":"e_1_3_2_2_33_1","volume-title":"Pocket: Elastic ephemeral storage for serverless analytics. In OSDI. 427--444.","author":"Klimovic Ana","year":"2018","unstructured":"Ana Klimovic, Yawen Wang, Patrick Stuedi, Animesh Trivedi, Jonas Pfefferle, and Christos Kozyrakis. 2018. Pocket: Elastic ephemeral storage for serverless analytics. In OSDI. 427--444."},{"key":"e_1_3_2_2_34_1","volume-title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations. In ICLR.","author":"Lan Zhenzhong","year":"2020","unstructured":"Zhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel, Piyush Sharma, and Radu Soricut. 2020. ALBERT: A Lite BERT for Self-supervised Learning of Language Representations. In ICLR."},{"key":"e_1_3_2_2_35_1","volume-title":"Meihui Zhang, Kaiping Zheng, Lei Zhu, Gang Chen, Feiyi Fan, Qian Lin, Kee Yuan Ngiam, and Beng Chin Ooi.","author":"Luo Zhaojing","year":"2021","unstructured":"Zhaojing Luo, Sai Ho Yeung, Meihui Zhang, Kaiping Zheng, Lei Zhu, Gang Chen, Feiyi Fan, Qian Lin, Kee Yuan Ngiam, and Beng Chin Ooi. 2021. MLCask: Efficient Management of Component Evolution in Collaborative Data Analytics Pipelines. In ICDE. 1655--1666."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"crossref","unstructured":"Pascal Maissen Pascal Felber Peter G. Kropf and Valerio Schiavoni. 2020. FaaSdom: a benchmark suite for serverless computing. In DEBS. 73--84.","DOI":"10.1145\/3401025.3401738"},{"key":"e_1_3_2_2_37_1","volume-title":"Savagaonkar","author":"McKeen Frank","year":"2013","unstructured":"Frank McKeen, Ilya Alexandrovich, Alex Berenzon, Carlos V. Rozas, Hisham Shafi, Vedvyas Shanbhogue, and Uday R. Savagaonkar. 2013. Innovative instructions and software model for isolated execution. In HASP. 10."},{"key":"e_1_3_2_2_38_1","unstructured":"Microsoft. 2021. Microsoft Azure Machine Learning. https:\/\/azure.microsoft.com\/en-us\/services\/machine-learning."},{"key":"e_1_3_2_2_39_1","unstructured":"Microsoft. 2021. Onnx Runtime. https:\/\/github.com\/microsoft\/onnxruntime."},{"key":"e_1_3_2_2_40_1","volume-title":"Lambada: Interactive Data Analytics on Cold Data Using Serverless Cloud Infrastructure. In SIGMOD. 115--130.","author":"M\u00fcller Ingo","year":"2020","unstructured":"Ingo M\u00fcller, Renato Marroquin, and Gustavo Alonso. 2020. Lambada: Interactive Data Analytics on Cold Data Using Serverless Cloud Infrastructure. In SIGMOD. 115--130."},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2807410"},{"key":"e_1_3_2_2_42_1","unstructured":"OpenWhisk. 2021. Open Source Serverless Cloud Platform. https:\/\/openwhisk.apache.org\/."},{"key":"e_1_3_2_2_43_1","volume-title":"David J. DeWitt, and Samuel Madden.","author":"Perron Matthew","year":"2020","unstructured":"Matthew Perron, Raul Castro Fernandez, David J. DeWitt, and Samuel Madden. 2020. Starling: A Scalable Query Engine on Cloud Functions. In SIGMOD. 131--141."},{"key":"e_1_3_2_2_44_1","unstructured":"Qifan Pu Shivaram Venkataraman and Ion Stoica. 2019. Shuffling Fast and Slow: Scalable Analytics on Serverless Infrastructure. In NSDI."},{"key":"e_1_3_2_2_45_1","volume-title":"Wong","author":"Rajabi Ali","year":"2012","unstructured":"Ali Rajabi and Johnny W. Wong. 2012. MMPP Characterization of Web Application Traffic. In MASCOTS. 107--114."},{"key":"e_1_3_2_2_46_1","volume-title":"Serverless Computing: Opportunities and Challenges. CoRR abs\/1911.01296","author":"Shafiei Hossein","year":"2019","unstructured":"Hossein Shafiei and Ahmad Khonsari. 2019. Serverless Computing: Opportunities and Challenges. CoRR abs\/1911.01296 (2019)."},{"key":"e_1_3_2_2_47_1","volume-title":"numpywren: serverless linear algebra. CoRR abs\/1810.09679","author":"Shankar Vaishaal","year":"2018","unstructured":"Vaishaal Shankar, Karl Krauth, Qifan Pu, Eric Jonas, Shivaram Venkataraman, Ion Stoica, Benjamin Recht, and Jonathan Ragan-Kelley. 2018. numpywren: serverless linear algebra. CoRR abs\/1810.09679 (2018)."},{"key":"e_1_3_2_2_48_1","unstructured":"Karen Simonyan and Andrew Zisserman. 2015. Very Deep Convolutional Networks for Large-Scale Image Recognition. In ICLR."},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.14778\/3407790.3407836"},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"crossref","unstructured":"Dmitrii Ustiugov Plamen Petrov Marios Kogias Edouard Bugnion and Boris Grot. 2021. Benchmarking analysis and optimization of serverless function snapshots. In ASPLOS. 559--572.","DOI":"10.1145\/3410279"},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"crossref","unstructured":"Leonid Velikovich Ian Williams Justin Scheiner Petar Aleksic Pedro Moreno and Michael Riley. 2018. Semantic Lattice Processing in Contextual Automatic Speech Recognition for Google Assistant. In Interspeech.","DOI":"10.21437\/Interspeech.2018-2453"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"crossref","unstructured":"Hao Wang Di Niu and Baochun Li. 2019. Distributed Machine Learning with a Serverless Architecture. In INFOCOM. 1288--1296.","DOI":"10.1109\/INFOCOM.2019.8737391"},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.14778\/3282495.3282499"},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3003665.3003669"},{"key":"e_1_3_2_2_55_1","volume-title":"Boxer: Data Analytics on Network-enabled Serverless Platforms. In CIDR.","author":"Wawrzoniak Michal","year":"2021","unstructured":"Michal Wawrzoniak, Ingo M\u00fcller, Gustavo Alonso, and Rodrigo Bruno. 2021. Boxer: Data Analytics on Network-enabled Serverless Platforms. In CIDR."},{"key":"e_1_3_2_2_56_1","unstructured":"Tianyi Yu Qingyuan Liu Dong Du Yubin Xia Binyu Zang Ziqian Lu Pingchao Yang Chenggang Qin and Haibo Chen. 2020. Characterizing serverless platforms with serverlessbench. In SoCC. 30--44."},{"key":"e_1_3_2_2_57_1","unstructured":"Chengliang Zhang Minchen Yu Wei Wang and Feng Yan. 2019. MArk: Exploiting Cloud Services for Cost-Effective SLO-Aware Machine Learning Inference Serving. In USENIX ATC. 1049--1062."},{"key":"e_1_3_2_2_58_1","volume-title":"Joseph E. Gonzalez, and Ion Stoica.","author":"Zheng Wenting","year":"2017","unstructured":"Wenting Zheng, Ankur Dave, Jethro G. Beekman, Raluca Ada Popa, Joseph E. Gonzalez, and Ion Stoica. 2017. Opaque: An Oblivious and Encrypted Distributed Analytics Platform. In NSDI. 283--298."}],"event":{"name":"SIGMOD\/PODS '22: International Conference on Management of Data","location":"Philadelphia PA USA","acronym":"SIGMOD\/PODS '22","sponsor":["SIGMOD ACM Special Interest Group on Management of Data"]},"container-title":["Proceedings of the 2022 International Conference on Management of Data"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3514221.3517905","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3514221.3517905","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:10:06Z","timestamp":1750183806000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3514221.3517905"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,10]]},"references-count":58,"alternative-id":["10.1145\/3514221.3517905","10.1145\/3514221"],"URL":"https:\/\/doi.org\/10.1145\/3514221.3517905","relation":{},"subject":[],"published":{"date-parts":[[2022,6,10]]},"assertion":[{"value":"2022-06-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}