{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,24]],"date-time":"2026-10-24T06:48:57Z","timestamp":1792824537847,"version":"4.5.0"},"reference-count":52,"publisher":"Association for Computing Machinery (ACM)","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Proc. VLDB Endow."],"published-print":{"date-parts":[[2021,9]]},"abstract":"<jats:p>\n                    Cardinality estimation is core to the query optimizers of DBMSs. Non-learned methods, especially based on histograms and samplings, have been widely used in commercial and open-source DBMSs. Nevertheless, histograms and samplings can only be used to summarize one or few columns, which fall short of capturing the joint data distribution over an arbitrary combination of columns, because of the oversimplification of histograms and samplings over the original relational table(s). Consequently, these traditional methods typically make bad predictions for hard cases such as queries over multiple columns, with multiple predicates, and joins between multiple tables. Recently,\n                    <jats:italic>learned<\/jats:italic>\n                    cardinality estimators have been widely studied. Because these learned estimators can better capture the data distribution and query characteristics, empowered by the recent advance of (deep learning) models, they outperform non-learned methods on many cases. The goals of this paper are to provide a design space exploration of learned cardinality estimators and to have a comprehensive comparison of the SOTA learned approaches so as to provide a guidance for practitioners to decide what method to use under various practical scenarios.\n                  <\/jats:p>","DOI":"10.14778\/3485450.3485459","type":"journal-article","created":{"date-parts":[[2022,1,14]],"date-time":"2022-01-14T18:26:50Z","timestamp":1642184810000},"page":"85-97","source":"Crossref","is-referenced-by-count":86,"title":["Learned cardinality estimation"],"prefix":"10.14778","volume":"15","author":[{"given":"Ji","family":"Sun","sequence":"first","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jintao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhaoyan","family":"Sun","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guoliang","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nan","family":"Tang","sequence":"additional","affiliation":[{"name":"Qatar Computing Research Institute"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,1,14]]},"reference":[{"key":"e_1_2_1_1_1","unstructured":"https:\/\/github.com\/andreaskipf\/learnedcardinalities.  https:\/\/github.com\/andreaskipf\/learnedcardinalities."},{"key":"e_1_2_1_2_1","unstructured":"https:\/\/github.com\/datamanagementlab\/deepdb-public.  https:\/\/github.com\/datamanagementlab\/deepdb-public."},{"key":"e_1_2_1_3_1","unstructured":"https:\/\/github.com\/illinoisdata\/quicksel.  https:\/\/github.com\/illinoisdata\/quicksel."},{"key":"e_1_2_1_4_1","unstructured":"https:\/\/github.com\/martinkiefer\/feedback-kde.  https:\/\/github.com\/martinkiefer\/feedback-kde."},{"key":"e_1_2_1_5_1","unstructured":"https:\/\/github.com\/neurocard\/neurocard.  https:\/\/github.com\/neurocard\/neurocard."},{"key":"e_1_2_1_6_1","unstructured":"https:\/\/github.com\/pgmpy\/pgmpy.  https:\/\/github.com\/pgmpy\/pgmpy."},{"key":"e_1_2_1_7_1","volume-title":"Bagging predictors","author":"Breiman L.","year":"1994","unstructured":"Breiman , L. Bagging predictors , 1994 . Breiman, L. Bagging predictors, 1994."},{"key":"e_1_2_1_8_1","volume-title":"Wadsworth","author":"Breiman L.","year":"1984","unstructured":"Breiman , L. , Friedman , J. H. , Olshen , R. A. , and Stone , C. J . Classification and Regression Trees . Wadsworth , 1984 . Breiman, L., Friedman, J. H., Olshen, R. A., and Stone, C. J. Classification and Regression Trees. Wadsworth, 1984."},{"key":"e_1_2_1_9_1","unstructured":"Carvalho A. Scoring functions for learning bayesian networks.  Carvalho A. Scoring functions for learning bayesian networks."},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1968.1054142"},{"key":"e_1_2_1_11_1","volume-title":"UCI machine learning repository","author":"Dua D.","year":"2017","unstructured":"Dua , D. , and Graff , C . UCI machine learning repository , 2017 . Dua, D., and Graff, C. UCI machine learning repository, 2017."},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.14778\/3329772.3329780"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/375663.375727"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/s41019-019-00115-y"},{"key":"e_1_2_1_15_1","volume-title":"Is query optimization a \"solved\" problem?","author":"Guy Lohman","year":"2014","unstructured":"Guy Lohman . Is query optimization a \"solved\" problem? , 2014 . https:\/\/dsf.berkeley.edu\/cs286\/papers\/queryopt-sigmodblog2014.pdf. Guy Lohman. Is query optimization a \"solved\" problem?, 2014. https:\/\/dsf.berkeley.edu\/cs286\/papers\/queryopt-sigmodblog2014.pdf."},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3318464.3389741"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2723372.2749438"},{"key":"e_1_2_1_18_1","first-page":"7","article-title":"Deepdb: Learn from data, not from queries! Proc","volume":"13","author":"Hilprecht B.","year":"2020","unstructured":"Hilprecht , B. , Schmidt , A. , Kulessa , M. , Molina , A. , Kersting , K. , and Binnig , C . Deepdb: Learn from data, not from queries! Proc . VLDB Endow. 13 , 7 ( 2020 ), 992--1005. Hilprecht, B., Schmidt, A., Kulessa, M., Molina, A., Kersting, K., and Binnig, C. Deepdb: Learn from data, not from queries! Proc. VLDB Endow. 13, 7 (2020), 992--1005.","journal-title":"VLDB Endow."},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.79.8.2554"},{"key":"e_1_2_1_20_1","volume-title":"https:\/\/www.imdb.com\/","author":"Db","year":"2019","unstructured":"IM Db .com. https:\/\/www.imdb.com\/ , 2019 . IMDb.com. https:\/\/www.imdb.com\/, 2019."},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/B978-012722442-8\/50011-2"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/73007.73049"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.14778\/3151106.3151112"},{"key":"e_1_2_1_24_1","volume-title":"9th Biennial Conference on Innovative Data Systems Research, CIDR 2019, Asilomar, CA, USA, January 13-16, 2019, Online Proceedings","author":"Kipf A.","year":"2019","unstructured":"Kipf , A. , Kipf , T. , Radke , B. , Leis , V. , Boncz , P. A. , and Kemper , A . Learned cardinalities: Estimating correlated joins with deep learning . In 9th Biennial Conference on Innovative Data Systems Research, CIDR 2019, Asilomar, CA, USA, January 13-16, 2019, Online Proceedings ( 2019 ), www.cidrdb.org. Kipf, A., Kipf, T., Radke, B., Leis, V., Boncz, P. A., and Kemper, A. Learned cardinalities: Estimating correlated joins with deep learning. In 9th Biennial Conference on Innovative Data Systems Research, CIDR 2019, Asilomar, CA, USA, January 13-16, 2019, Online Proceedings (2019), www.cidrdb.org."},{"key":"e_1_2_1_25_1","volume-title":"Probabilistic Graphical Models: Principles and Techniques - Adaptive Computation and Machine Learning","author":"Koller D.","year":"2009","unstructured":"Koller , D. , and Friedman , N . Probabilistic Graphical Models: Principles and Techniques - Adaptive Computation and Machine Learning . The MIT Press , 2009 . Koller, D., and Friedman, N. Probabilistic Graphical Models: Principles and Techniques - Adaptive Computation and Machine Learning. The MIT Press, 2009."},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.14778\/2850583.2850594"},{"key":"e_1_2_1_28_1","volume-title":"CIDR","author":"Leis V.","year":"2017","unstructured":"Leis , V. , Radke , B. , Gubichev , A. , Kemper , A. , and Neumann , T . Cardinality estimation done right: Index-based join sampling . In CIDR ( 2017 ). Leis, V., Radke, B., Gubichev, A., Kemper, A., and Neumann, T. Cardinality estimation done right: Index-based join sampling. In CIDR (2017)."},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3448016.3457542"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.14778\/3476311.3476405"},{"key":"e_1_2_1_31_1","volume-title":"TKDE","author":"Li G.","year":"2021","unstructured":"Li , G. , Zhou , X. , and Chai , C . AI meets database: A survey . In TKDE ( 2021 ). Li, G., Zhou, X., and Chai, C. AI meets database: A survey. In TKDE (2021)."},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.14778\/3476311.3476380"},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.26599\/BDMA.2019.9020019"},{"key":"e_1_2_1_34_1","first-page":"129","volume-title":"Mixture Models","author":"Lindsay B. G.","year":"2010","unstructured":"Lindsay , B. G. , and Stewart , M . Mixture Models . Palgrave Macmillan UK , London , 2010 , pp. 129 -- 138 . Lindsay, B. G., and Stewart, M. Mixture Models. Palgrave Macmillan UK, London, 2010, pp. 129--138."},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/93605.93611"},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.14778\/1687627.1687738"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-52342-1_23"},{"key":"e_1_2_1_38_1","volume-title":"An empirical analysis of deep learning for cardinality estimation. CoRR abs\/1905.06425","author":"Ortiz J.","year":"2019","unstructured":"Ortiz , J. , Balazinska , M. , Gehrke , J. , and Keerthi , S. S . An empirical analysis of deep learning for cardinality estimation. CoRR abs\/1905.06425 ( 2019 ). Ortiz, J., Balazinska, M., Gehrke, J., and Keerthi, S. S. An empirical analysis of deep learning for cardinality estimation. CoRR abs\/1905.06425 (2019)."},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3318464.3389727"},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00116037"},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.14778\/3368289.3368296"},{"key":"e_1_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/s41019-020-00117-1"},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.14778\/3402707.3402724"},{"key":"e_1_2_1_44_1","volume-title":"Are we ready for learned cardinality estimation? CoRR abs\/2012.06743","author":"Wang X.","year":"2020","unstructured":"Wang , X. , Qu , C. , Wu , W. , Wang , J. , and Zhou , Q . Are we ready for learned cardinality estimation? CoRR abs\/2012.06743 ( 2020 ). Wang, X., Qu, C., Wu, W., Wang, J., and Zhou, Q. Are we ready for learned cardinality estimation? CoRR abs\/2012.06743 (2020)."},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3329859.3329875"},{"key":"e_1_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/2882903.2882914"},{"key":"e_1_2_1_47_1","volume-title":"https:\/\/www.xuetangx.com\/global","author":"XueTang T.","year":"2019","unstructured":"XueTang , T. https:\/\/www.xuetangx.com\/global , 2019 . XueTang, T. https:\/\/www.xuetangx.com\/global, 2019."},{"key":"e_1_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.14778\/3421424.3421432"},{"key":"e_1_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.14778\/3368289.3368294"},{"key":"e_1_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE48307.2020.00116"},{"key":"e_1_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3183713.3183739"},{"key":"e_1_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.14778\/3397230.3397238"}],"container-title":["Proceedings of the VLDB Endowment"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.14778\/3485450.3485459","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,28]],"date-time":"2022-12-28T05:42:52Z","timestamp":1672206172000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.14778\/3485450.3485459"}},"subtitle":["a design space exploration and a comparative evaluation"],"short-title":[],"issued":{"date-parts":[[2021,9]]},"references-count":52,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,9]]}},"alternative-id":["10.14778\/3485450.3485459"],"URL":"https:\/\/doi.org\/10.14778\/3485450.3485459","relation":{},"ISSN":["2150-8097"],"issn-type":[{"value":"2150-8097","type":"print"}],"subject":[],"published":{"date-parts":[[2021,9]]}}}