{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,28]],"date-time":"2026-10-28T08:32:39Z","timestamp":1793176359596,"version":"4.5.0"},"publisher-location":"New York, NY, USA","reference-count":59,"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:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"German Ministry for Education and Research as BIFOLD - Berlin Institute for the Foundations of Learning and Data","award":["1IS18025A, 01IS18037A"],"award-info":[{"award-number":["1IS18025A, 01IS18037A"]}]},{"name":"German Federal Ministry for Economic Affairs and Climate Action, Project ?ExDRa?","award":["1MD19002B"],"award-info":[{"award-number":["1MD19002B"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,6,10]]},"DOI":"10.1145\/3514221.3526186","type":"proceedings-article","created":{"date-parts":[[2022,6,12]],"date-time":"2022-06-12T02:33:49Z","timestamp":1655001229000},"page":"1962-1976","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["Materialization and Reuse Optimizations for Production Data Science Pipelines"],"prefix":"10.1145","author":[{"given":"Behrouz","family":"Derakhshan","sequence":"first","affiliation":[{"name":"DFKI GmbH, Berlin, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alireza","family":"Rezaei Mahdiraji","sequence":"additional","affiliation":[{"name":"Yara Digital Production, Berlin, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zoi","family":"Kaoudi","sequence":"additional","affiliation":[{"name":"TU Berlin, Berlin, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tilmann","family":"Rabl","sequence":"additional","affiliation":[{"name":"HPI & University of Potsdam, Potsdam, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Volker","family":"Markl","sequence":"additional","affiliation":[{"name":"TU Berlin & DFKI GmbH, Berlin, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,6,11]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"On the difficulty of warm-starting neural network training. arXiv preprint arXiv:1910.08475","author":"Ash Jordan T","year":"2019","unstructured":"Jordan T Ash and Ryan P Adams. 2019. On the difficulty of warm-starting neural network training. arXiv preprint arXiv:1910.08475 (2019)."},{"key":"e_1_3_2_1_2_1","volume-title":"Searching for exotic particles in high-energy physics with deep learning. Nature communications","author":"Baldi Pierre","year":"2014","unstructured":"Pierre Baldi, Peter Sadowski, and Daniel Whiteson. 2014. Searching for exotic particles in high-energy physics with deep learning. Nature communications, Vol. 5, 1 (2014), 1--9."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098021"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.14778\/2824032.2824035"},{"key":"e_1_3_2_1_5_1","volume-title":"NYC Taxi Trip - Public. kaggle.com\/jeffreycbw\/nyc-taxi-trip-public-0--37399-private-0--37206 Retrieved","author":"Chung Jeffrey","year":"2021","unstructured":"Jeffrey Chung. 2020. NYC Taxi Trip - Public. kaggle.com\/jeffreycbw\/nyc-taxi-trip-public-0--37399-private-0--37206 Retrieved August 23, 2021 from"},{"key":"e_1_3_2_1_6_1","unstructured":"Google Cloud. 2020. MLOps: Continuous delivery and automation pipelines in machine learning. https:\/\/cloud.google.com\/solutions\/machine-learning\/mlops-continuous-delivery-and-automation-pipelines-in-machine-learning Retrieved November 16 2020 from"},{"key":"e_1_3_2_1_7_1","unstructured":"Daniel Crankshaw Peter Bailis Joseph E Gonzalez Haoyuan Li et al. 2014. The missing piece in complex analytics: Low latency scalable model management and serving with velox. arXiv preprint arXiv:1409.3809 (2014)."},{"key":"e_1_3_2_1_8_1","volume-title":"14th USENIX Symposium on Networked Systems Design and Implementation (NSDI 17)","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 14th USENIX Symposium on Networked Systems Design and Implementation (NSDI 17). 613--627."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0022-0000(03)00031-X"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.2307\/2981683"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/1629175.1629198"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3318464.3389715"},{"key":"e_1_3_2_1_13_1","volume-title":"Tilmann Rabl, and Volker Markl.","author":"Derakhshan Behrouz","year":"2019","unstructured":"Behrouz Derakhshan, Alireza Rezaei Mahdiraji, Tilmann Rabl, and Volker Markl. 2019. Continuous Deployment of Machine Learning Pipelines.. In EDBT. 397--408."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","unstructured":"Yadolah Dodge. 2008. Kolmogorov--Smirnov Test .Springer New York New York NY 283--287. https:\/\/doi.org\/10.1007\/978-0--387--32833--1_214","DOI":"10.1007\/978-0--387--32833--1_214"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.14778\/2168651.2168659"},{"key":"e_1_3_2_1_16_1","volume-title":"Proc. LSDS-IR","volume":"8","author":"Michael Isard Dennis Fetterly Yuan Yu","year":"2009","unstructured":"Yuan Yu Michael Isard Dennis Fetterly, Mihai Budiu, \u00dalfar Erlingsson, and Pradeep Kumar Gunda Jon Currey. 2009. DryadLINQ: A system for general-purpose distributed data-parallel computing using a high-level language. Proc. LSDS-IR, Vol. 8 (2009)."},{"key":"e_1_3_2_1_17_1","volume-title":"Jost Tobias Springenberg, et al","author":"Feurer Matthias","year":"2019","unstructured":"Matthias Feurer, Aaron Klein, Katharina Eggensperger, Jost Tobias Springenberg, et al. 2019. Auto-sklearn: efficient and robust automated machine learning. In Automated Machine Learning. Springer, Cham, 113--134."},{"key":"e_1_3_2_1_18_1","volume-title":"Deep learning","author":"Goodfellow Ian","unstructured":"Ian Goodfellow, Yoshua Bengio, and Aaron Courville. 2016. Deep learning .MIT press."},{"key":"e_1_3_2_1_19_1","unstructured":"Nirmal Govind. 2017. A\/B Testing and Beyond: Improving the Netflix Streaming Experience with Experimentation and Data Science. https:\/\/netflixtechblog.com\/a-b-testing-and-beyond-improving-the-netflix-streaming-experience-with-experimentation-and-data-5b0ae9295bdf Retrieved June 08 2021 from"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"crossref","unstructured":"Jim Gray Surajit Chaudhuri Adam Bosworth Andrew Layman et al. 1997. Data cube: A relational aggregation operator generalizing group-by cross-tab and sub-totals. Data mining and knowledge discovery Vol. 1 1 (1997) 29--53.","DOI":"10.1023\/A:1009726021843"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/376284.375670"},{"key":"e_1_3_2_1_22_1","volume-title":"Proceedings of the 9th USENIX Conference on Operating Systems Design and Implementation","author":"Gunda Pradeep Kumar","year":"2010","unstructured":"Pradeep Kumar Gunda, Lenin Ravindranath, Chandramohan A. Thekkath, et al. 2010. Nectar: Automatic Management of Data and Computation in Datacenters. In Proceedings of the 9th USENIX Conference on Operating Systems Design and Implementation (Vancouver, BC, Canada) (OSDI'10). USENIX Association, USA, 75--88."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020--2649--2"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.14778\/3352063.3352096"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.14778\/3236187.3236199"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/2648584.2648589"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"crossref","unstructured":"Ihab F Ilyas and Xu Chu. 2019. Data cleaning .ACM.","DOI":"10.1145\/3310205"},{"key":"e_1_3_2_1_28_1","volume-title":"New York City Taxi Trip Duration Competition. https:\/\/www.kaggle.com\/c\/nyc-taxi-trip-duration\/ Retrieved","year":"2021","unstructured":"Kaggle. 2020. New York City Taxi Trip Duration Competition. https:\/\/www.kaggle.com\/c\/nyc-taxi-trip-duration\/ Retrieved September 10, 2021 from"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.14778\/3372716.3372718"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403290"},{"key":"e_1_3_2_1_31_1","volume-title":"https:\/\/aws.amazon.com\/blogs\/machine-learning\/a-b-testing-ml-models-in-production-using-amazon-sagemaker\/ Retrieved","author":"Kavanagh Kieran","year":"2021","unstructured":"Kieran Kavanagh, David Nigenda, and Aakash Pydi. 2020. A\/B Testing ML models in production using Amazon SageMaker. https:\/\/aws.amazon.com\/blogs\/machine-learning\/a-b-testing-ml-models-in-production-using-amazon-sagemaker\/ Retrieved February 26, 2021 from"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/1142473.1142543"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.5555\/1248547.1248616"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553462"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/2206869.2206874"},{"key":"e_1_3_2_1_36_1","volume-title":"Big Data: Principles and best practices of scalable real-time data systems .Manning.","author":"Marz Nathan","year":"2013","unstructured":"Nathan Marz and James Warren. 2013. Big Data: Principles and best practices of scalable real-time data systems .Manning."},{"key":"e_1_3_2_1_37_1","volume-title":"kaggle.com\/ahmedmurad1990\/nyc-taxi Retrieved","author":"Mazen Ahmed","year":"2021","unstructured":"Ahmed Mazen and Motaz Saad. 2021. NYC Taxi. kaggle.com\/ahmedmurad1990\/nyc-taxi Retrieved August 23, 2021 from"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.5555\/2946645.2946679"},{"key":"e_1_3_2_1_39_1","volume-title":"kaggle.com\/quentinmonmousseau\/ml-workflow-lightgbm-0--37-randomforest-0--39 Retrieved","author":"Monmousseau Quentin","year":"2021","unstructured":"Quentin Monmousseau. 2019. ML Workflow. kaggle.com\/quentinmonmousseau\/ml-workflow-lightgbm-0--37-randomforest-0--39 Retrieved August 23, 2021 from"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.14778\/1920841.1920906"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.5555\/1953048.2078195"},{"key":"e_1_3_2_1_42_1","volume-title":"Proceedings of Machine Learning and Systems, A. Talwalkar, V. Smith, and M. Zaharia (Eds.)","volume":"1","author":"Renggli Cedric","year":"2019","unstructured":"Cedric Renggli, Bojan Karlavs, Bolin Ding, Feng Liu, Kevin Schawinski, Wentao Wu, and Ce Zhang. 2019. Continuous Integration of Machine Learning Models with ease.ml\/ci: Towards a Rigorous Yet Practical Treatment. In Proceedings of Machine Learning and Systems, A. Talwalkar, V. Smith, and M. Zaharia (Eds.), Vol. 1. 322--333."},{"key":"e_1_3_2_1_43_1","volume-title":"IJCAI 2001 workshop on empirical methods in artificial intelligence","volume":"3","author":"Irina","unstructured":"Irina Rish et al. 2001. An empirical study of the naive Bayes classifier. In IJCAI 2001 workshop on empirical methods in artificial intelligence, Vol. 3. 41--46."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/342009.335419"},{"key":"e_1_3_2_1_45_1","unstructured":"Sebastian Schelter Felix Biessmann Tim Januschowski David Salinas Stephan Seufert and Gyuri Szarvas. 2018. On challenges in machine learning model management. (2018)."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/42201.42203"},{"key":"e_1_3_2_1_47_1","volume-title":"Architecting data lakes: data management architectures for advanced business use cases","author":"Sharma Ben","unstructured":"Ben Sharma. 2018. Architecting data lakes: data management architectures for advanced business use cases .O'Reilly Media."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.14778\/2809974.2809991"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.14778\/2752939.2752940"},{"key":"e_1_3_2_1_50_1","volume-title":"NYC Taxi and Limousine Commission (TLC) Trip Record Data. https:\/\/www1.nyc.gov\/site\/tlc\/about\/tlc-trip-record-data.page Retrieved","author":"NYC Taxi and Limousine Commission (TLC). 2021.","year":"2021","unstructured":"NYC Taxi and Limousine Commission (TLC). 2021. NYC Taxi and Limousine Commission (TLC) Trip Record Data. https:\/\/www1.nyc.gov\/site\/tlc\/about\/tlc-trip-record-data.page Retrieved August 23, 2021 from"},{"key":"e_1_3_2_1_51_1","volume-title":"Sebastian Bre\u00df, Asterios Katsifodimos, Tilmann Rabl, and Volker Markl.","author":"Traub Jonas","year":"2019","unstructured":"Jonas Traub, Philipp M Grulich, Alejandro Rodr'iguez Cu\u00e9llar, Sebastian Bre\u00df, Asterios Katsifodimos, Tilmann Rabl, and Volker Markl. 2019. Efficient Window Aggregation with General Stream Slicing. In EDBT. 97--108."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/2623330.2623661"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3076246.3076248"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3183713.3196934"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.14778\/2732232.2732234"},{"key":"e_1_3_2_1_56_1","volume-title":"Helix: Holistic optimization for accelerating iterative machine learning. arXiv preprint arXiv:1812.05762","author":"Xin Doris","year":"2018","unstructured":"Doris Xin, Stephen Macke, Litian Ma, Jialin Liu, Shuchen Song, and Aditya Parameswaran. 2018. Helix: Holistic optimization for accelerating iterative machine learning. arXiv preprint arXiv:1812.05762 (2018)."},{"key":"e_1_3_2_1_57_1","volume-title":"9th USENIX Symposium on Networked Systems Design and Implementation (NSDI 12)","author":"Zaharia Matei","year":"2012","unstructured":"Matei Zaharia, Mosharaf Chowdhury, Tathagata Das, Ankur Dave, Justin Ma, Murphy McCauly, Michael J Franklin, Scott Shenker, and Ion Stoica. 2012. Resilient distributed datasets: A fault-tolerant abstraction for in-memory cluster computing. In 9th USENIX Symposium on Networked Systems Design and Implementation (NSDI 12). 15--28."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/2934664"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/2877204"}],"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\/3514221.3526186","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3514221.3526186","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:10:14Z","timestamp":1750183814000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3514221.3526186"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,10]]},"references-count":59,"alternative-id":["10.1145\/3514221.3526186","10.1145\/3514221"],"URL":"https:\/\/doi.org\/10.1145\/3514221.3526186","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"}}]}}