{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T04:04:23Z","timestamp":1784261063888,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":37,"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":[{"DOI":"10.13039\/501100001459","name":"Ministry of Education - Singapore","doi-asserted-by":"publisher","award":["MOE2019-T2-2-181, RG114\/19(S)"],"award-info":[{"award-number":["MOE2019-T2-2-181, RG114\/19(S)"]}],"id":[{"id":"10.13039\/501100001459","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,6,10]]},"DOI":"10.1145\/3514221.3526168","type":"proceedings-article","created":{"date-parts":[[2022,6,12]],"date-time":"2022-06-12T02:33:49Z","timestamp":1655001229000},"page":"1542-1555","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":15,"title":["SAM: Database Generation from Query Workloads with Supervised Autoregressive Models"],"prefix":"10.1145","author":[{"given":"Jingyi","family":"Yang","sequence":"first","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peizhi","family":"Wu","sequence":"additional","affiliation":[{"name":"University of Pennsylvania, Philadelphia, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gao","family":"Cong","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tieying","family":"Zhang","sequence":"additional","affiliation":[{"name":"ByteDance Inc., Mountain View, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiao","family":"He","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,6,11]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"[n.d.]. Replaying a Database Workload Oracle. https:\/\/docs.oracle.com\/cd\/E11882_01\/server.112\/e41481\/dbr_replay.htm#RATUG131."},{"key":"e_1_3_2_2_2_1","unstructured":"[n.d.]. UCI machine learning repository. https:\/\/archive.ics.uci.edu\/ml\/index.php."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/375551.375602"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"crossref","unstructured":"Arvind Arasu Raghav Kaushik and Jian Li. 2011. Data generation using declarative constraints. In SIGMOD. 685--696.","DOI":"10.1145\/1989323.1989395"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/1247480.1247520"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/1401890.1401904"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"crossref","unstructured":"Nicolas Bruno Surajit Chaudhuri and Luis Gravano. 2001. STHoles: a multidimensional workload-aware histogram. In SIGMOD. 211--222.","DOI":"10.1145\/376284.375686"},{"key":"e_1_3_2_2_8_1","unstructured":"Edward Choi Siddharth Biswal Bradley Malin Jon Duke Walter F Stewart and Jimeng Sun. 2017. Generating multi-label discrete patient records using generative adversarial networks. In Machine learning for healthcare conference. PMLR."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1561\/1900000004"},{"key":"e_1_3_2_2_10_1","volume-title":"Privacy-preserving data mining","author":"Domingo-Ferrer Josep","unstructured":"Josep Domingo-Ferrer. 2008. A survey of inference control methods for privacy- preserving data mining. In Privacy-preserving data mining. Springer, 53--80."},{"key":"e_1_3_2_2_11_1","volume-title":"Relational data synthesis using generative adversarial networks: A design space exploration. arXiv preprint arXiv:2008.12763","author":"Fan Ju","year":"2020","unstructured":"Ju Fan, Tongyu Liu, Guoliang Li, Junyou Chen, Yuwei Shen, and Xiaoyong Du. 2020. Relational data synthesis using generative adversarial networks: A design space exploration. arXiv preprint arXiv:2008.12763 (2020)."},{"key":"e_1_3_2_2_12_1","volume-title":"International Conference on Machine Learning. PMLR, 881--889","author":"Germain Mathieu","year":"2015","unstructured":"Mathieu Germain, Karol Gregor, Iain Murray, and Hugo Larochelle. 2015. Made: Masked autoencoder for distribution estimation. In International Conference on Machine Learning. PMLR, 881--889."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"crossref","unstructured":"Lise Getoor Benjamin Taskar and Daphne Koller. 2001. Selectivity estimation using probabilistic models. In SIGMOD. 461--472.","DOI":"10.1145\/376284.375727"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"crossref","unstructured":"Benjamin Hilprecht Andreas Schmidt Moritz Kulessa Alejandro Molina Kristian Kersting and Carsten Binnig. 2020. DeepDB: Learn from Data not from Queries! VLDB 13 7 992--1005.","DOI":"10.14778\/3384345.3384349"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1952.10483446"},{"key":"e_1_3_2_2_16_1","unstructured":"Andreas Kipf Thomas Kipf Bernhard Radke Viktor Leis Peter Boncz and Alfons Kemper. 2019. Learned cardinalities: Estimating correlated joins with deep learning. In CIDR."},{"key":"e_1_3_2_2_17_1","volume-title":"Probabilistic graphical models: principles and techniques","author":"Koller Daphne","unstructured":"Daphne Koller and Nir Friedman. 2009. Probabilistic graphical models: principles and techniques. MIT press."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.14778\/2850583.2850594"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-017-0480-7"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2007.367856"},{"key":"e_1_3_2_2_21_1","unstructured":"Yuming Li Rong Zhang Xiaoyan Yang Zhenjie Zhang and Aoying Zhou. 2018. Touchstone: generating enormous query-aware test databases. In 2018 {USENIX} Annual Technical Conference ({USENIX} {ATC} 18). 575--586."},{"key":"e_1_3_2_2_22_1","first-page":"1","article-title":"Generating databases for query workloads","volume":"3","author":"Lo Eric","year":"2010","unstructured":"Eric Lo, Nick Cheng, and Wing-Kai Hon. 2010. Generating databases for query workloads. VLDB 3, 1--2 (2010), 848--859.","journal-title":"VLDB"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-014-0354-1"},{"key":"e_1_3_2_2_24_1","volume-title":"Inverse probability weighting. Bmj 352","author":"Mansournia Mohammad Ali","year":"2016","unstructured":"Mohammad Ali Mansournia and Douglas G Altman. 2016. Inverse probability weighting. Bmj 352 (2016)."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.14778\/1687627.1687738"},{"key":"e_1_3_2_2_26_1","volume-title":"An Empirical Analysis of Deep Learning for Cardinality Estimation. arXiv preprint arXiv:1905.06425","author":"Ortiz Jennifer","year":"2019","unstructured":"Jennifer Ortiz, Magdalena Balazinska, Johannes Gehrke, and S Sathiya Keerthi. 2019. An Empirical Analysis of Deep Learning for Cardinality Estimation. arXiv preprint arXiv:1905.06425 (2019)."},{"key":"e_1_3_2_2_27_1","unstructured":"George Papamakarios Theo Pavlakou and Iain Murray. 2017. Masked autoregressive flow for density estimation. In NIPS. 2338--2347."},{"key":"e_1_3_2_2_28_1","volume-title":"Data synthesis based on generative adversarial networks. arXiv preprint arXiv:1806.03384","author":"Park Noseong","year":"2018","unstructured":"Noseong Park, Mahmoud Mohammadi, Kshitij Gorde, Sushil Jajodia, Hongkyu Park, and Youngmin Kim. 2018. Data synthesis based on generative adversarial networks. arXiv preprint arXiv:1806.03384 (2018)."},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1994.10476818"},{"key":"e_1_3_2_2_30_1","volume-title":"Approximate query processing using deep generative models. arXiv preprint arXiv:1903.10000","author":"Thirumuruganathan Saravanan","year":"2019","unstructured":"Saravanan Thirumuruganathan, Shohedul Hasan, Nick Koudas, and Gautam Das. 2019. Approximate query processing using deep generative models. arXiv preprint arXiv:1903.10000 (2019)."},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.14778\/3402707.3402724"},{"key":"e_1_3_2_2_32_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez Lukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in neural information processing systems. 5998--6008."},{"key":"e_1_3_2_2_33_1","first-page":"210","article-title":"Towards a learning optimizer for shared clouds","volume":"12","author":"Wu Chenggang","year":"2018","unstructured":"Chenggang Wu, Alekh Jindal, Saeed Amizadeh, Hiren Patel, Wangchao Le, Shi Qiao, and Sriram Rao. 2018. Towards a learning optimizer for shared clouds. VLDB 12, 3 (2018), 210--222.","journal-title":"VLDB"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"crossref","unstructured":"Peizhi Wu and Gao Cong. 2021. A Unified Deep Model of Learning from both Data and Queries for Cardinality Estimation. In SIGMOD. 2009--2022.","DOI":"10.1145\/3448016.3452830"},{"key":"e_1_3_2_2_35_1","volume-title":"NeuroCard: One Cardinality Estimator for All Tables. PVLDB","author":"Yang Zongheng","year":"2021","unstructured":"Zongheng Yang, Amog Kamsetty, Sifei Luan, Eric Liang, Yan Duan, Xi Chen, and Ion Stoica. 2021. NeuroCard: One Cardinality Estimator for All Tables. PVLDB (2021)."},{"key":"e_1_3_2_2_36_1","first-page":"279","article-title":"Deep Unsupervised Cardinality Estimation","volume":"13","author":"Yang Zongheng","year":"2020","unstructured":"Zongheng Yang, Eric Liang, Amog Kamsetty, Chenggang Wu, Yan Duan, Xi Chen, Pieter Abbeel, Joseph M Hellerstein, Sanjay Krishnan, and Ion Stoica. 2020. Deep Unsupervised Cardinality Estimation. VLDB 13, 3, 279--292.","journal-title":"VLDB"},{"key":"e_1_3_2_2_37_1","unstructured":"Federico Zanettin. 2019. State of New York. Vehicle snowmobile and boat registrations. catalog.data.gov\/dataset\/vehicle-snowmobile-and-boat-registrations."}],"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\/3514221.3526168","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3514221.3526168","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:10:13Z","timestamp":1750183813000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3514221.3526168"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,10]]},"references-count":37,"alternative-id":["10.1145\/3514221.3526168","10.1145\/3514221"],"URL":"https:\/\/doi.org\/10.1145\/3514221.3526168","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"}}]}}