{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T20:34:38Z","timestamp":1780346078147,"version":"3.54.1"},"reference-count":51,"publisher":"Association for Computing Machinery (ACM)","issue":"7","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Proc. VLDB Endow."],"published-print":{"date-parts":[[2020,3]]},"abstract":"<jats:p>The typical approach for learned DBMS components is to capture the behavior by running a representative set of queries and use the observations to train a machine learning model. This workload-driven approach, however, has two major downsides. First, collecting the training data can be very expensive, since all queries need to be executed on potentially large databases. Second, training data has to be recollected when the workload or the database changes. To overcome these limitations, we take a different route and propose a new data-driven approach for learned DBMS components which directly supports changes of the workload and data without the need of retraining. Indeed, one may now expect that this comes at a price of lower accuracy since workload-driven approaches can make use of more information. However, this is not the case. The results of our empirical evaluation demonstrate that our data-driven approach not only provides better accuracy than state-ofthe- art learned components but also generalizes better to unseen queries.<\/jats:p>","DOI":"10.14778\/3384345.3384349","type":"journal-article","created":{"date-parts":[[2020,3,26]],"date-time":"2020-03-26T14:21:06Z","timestamp":1585232466000},"page":"992-1005","source":"Crossref","is-referenced-by-count":191,"title":["DeepDB"],"prefix":"10.14778","volume":"13","author":[{"given":"Benjamin","family":"Hilprecht","sequence":"first","affiliation":[{"name":"TU Darmstadt, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andreas","family":"Schmidt","sequence":"additional","affiliation":[{"name":"KIT &amp; Hochschule Karlsruhe, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Moritz","family":"Kulessa","sequence":"additional","affiliation":[{"name":"TU Darmstadt, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alejandro","family":"Molina","sequence":"additional","affiliation":[{"name":"TU Darmstadt, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kristian","family":"Kersting","sequence":"additional","affiliation":[{"name":"TU Darmstadt, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Carsten","family":"Binnig","sequence":"additional","affiliation":[{"name":"TU Darmstadt, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2020,3,26]]},"reference":[{"key":"e_1_2_1_1_1","unstructured":"Flights dataset. https:\/\/www.kaggle.com\/usdot\/flight-delays. Accessed: 2019-06-30.  Flights dataset. https:\/\/www.kaggle.com\/usdot\/flight-delays. Accessed: 2019-06-30."},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/2465351.2465355"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2012.64"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.5555\/3015812.3015951"},{"key":"e_1_2_1_5_1","first-page":"12","article-title":"Approximate query processing using wavelets","volume":"10","author":"Chakrabarti K.","year":"2000","unstructured":"K. Chakrabarti , M. Garofalakis , R. Rastogi , and K. Shim . Approximate query processing using wavelets . The VLDB Journal , 10 , 12 2000 . K. Chakrabarti, M. Garofalakis, R. Rastogi, and K. Shim. Approximate query processing using wavelets. The VLDB Journal, 10, 12 2000.","journal-title":"The VLDB Journal"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-006-0004-3"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.5555\/1622810.1622817"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.14778\/3329772.3329780"},{"key":"e_1_2_1_9_1","volume-title":"Idebench: A benchmark for interactive data exploration","author":"Eichmann P.","year":"2018","unstructured":"P. Eichmann , C. Binnig , T. Kraska , and E. Zgraggen . Idebench: A benchmark for interactive data exploration , 2018 . P. Eichmann, C. Binnig, T. Kraska, and E. Zgraggen. Idebench: A benchmark for interactive data exploration, 2018."},{"key":"e_1_2_1_10_1","first-page":"873","volume-title":"Learning the Structure of Sum-Product Networks. In International Conference on Machine Learning","author":"Gens R.","year":"2013","unstructured":"R. Gens and P. Domingos . Learning the Structure of Sum-Product Networks. In International Conference on Machine Learning , pages 873 -- 880 , 2013 . R. Gens and P. Domingos. Learning the Structure of Sum-Product Networks. In International Conference on Machine Learning, pages 873--880, 2013."},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/1989323.1989451"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/375663.375727"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.14778\/2904483.2904487"},{"key":"e_1_2_1_14_1","volume-title":"Multi-attribute selectivity estimation using deep learning. CoRR, abs\/1903.09999","author":"Hasan S.","year":"2019","unstructured":"S. Hasan , S. Thirumuruganathan , J. Augustine , N. Koudas , and G. Das . Multi-attribute selectivity estimation using deep learning. CoRR, abs\/1903.09999 , 2019 . S. Hasan, S. Thirumuruganathan, J. Augustine, N. Koudas, and G. Das. Multi-attribute selectivity estimation using deep learning. CoRR, abs\/1903.09999, 2019."},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.14778\/2350229.2350236"},{"key":"e_1_2_1_16_1","volume-title":"CIDR 2019, 9th Biennial Conference on Innovative Data Systems Research, Asilomar, CA, USA, January 13--16, 2019, Online Proceedings","author":"Kipf A.","year":"2019","unstructured":"A. Kipf , T. Kipf , B. Radke , V. Leis , P. A. Boncz , and A. Kemper . Learned cardinalities: Estimating correlated joins with deep learning . In CIDR 2019, 9th Biennial Conference on Innovative Data Systems Research, Asilomar, CA, USA, January 13--16, 2019, Online Proceedings , 2019 . A. Kipf, T. Kipf, B. Radke, V. Leis, P. A. Boncz, and A. Kemper. Learned cardinalities: Estimating correlated joins with deep learning. In CIDR 2019, 9th Biennial Conference on Innovative Data Systems Research, Asilomar, CA, USA, January 13--16, 2019, Online Proceedings, 2019."},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3183713.3196909"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.5555\/645924.671200"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.14778\/2850583.2850594"},{"key":"e_1_2_1_20_1","volume-title":"CIDR 2017, 8th Biennial Conference on Innovative Data Systems Research, Chaminade, CA, USA, January 8--11, 2017, Online Proceedings","author":"Leis V.","year":"2017","unstructured":"V. Leis , B. Radke , A. Gubichev , A. Kemper , and T. Neumann . Cardinality estimation done right: Index-based join sampling . In CIDR 2017, 8th Biennial Conference on Innovative Data Systems Research, Chaminade, CA, USA, January 8--11, 2017, Online Proceedings , 2017 . V. Leis, B. Radke, A. Gubichev, A. Kemper, and T. Neumann. Cardinality estimation done right: Index-based join sampling. In CIDR 2017, 8th Biennial Conference on Innovative Data Systems Research, Chaminade, CA, USA, January 8--11, 2017, Online Proceedings, 2017."},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2882903.2915235"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.5555\/2886444.2886453"},{"key":"e_1_2_1_23_1","first-page":"1","volume-title":"Advances in neural information processing systems","author":"Lopez-Paz D.","year":"2013","unstructured":"D. Lopez-Paz , P. Hennig , and B. Scholkopf . The randomized dependence coefficient . In Advances in neural information processing systems , pages 1 -- 9 , 2013 . D. Lopez-Paz, P. Hennig, and B. Scholkopf. The randomized dependence coefficient. In Advances in neural information processing systems, pages 1--9, 2013."},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3299869.3324958"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3299869.3324958"},{"key":"e_1_2_1_26_1","volume-title":"CIDR","author":"Malik T.","year":"2007","unstructured":"T. Malik , R. Burns , and N. Chawla . A black-box approach to query cardinality estimation . In CIDR , 2007 . T. Malik, R. Burns, and N. Chawla. A black-box approach to query cardinality estimation. In CIDR, 2007."},{"key":"e_1_2_1_27_1","volume-title":"Neo: A learned query optimizer. CoRR, abs\/1904.03711","author":"Marcus R.","year":"2019","unstructured":"R. Marcus , P. Negi , H. Mao , C. Zhang , M. Alizadeh , T. Kraska , O. Papaemmanouil , and N. Tatbul . Neo: A learned query optimizer. CoRR, abs\/1904.03711 , 2019 . R. Marcus, P. Negi, H. Mao, C. Zhang, M. Alizadeh, T. Kraska, O. Papaemmanouil, and N. Tatbul. Neo: A learned query optimizer. CoRR, abs\/1904.03711, 2019."},{"key":"e_1_2_1_28_1","volume-title":"AAAI","author":"Molina A.","year":"2017","unstructured":"A. Molina , S. Natarajan , and K. Kersting . Poisson Sum-Product Networks: A Deep Architecture for Tractable Multivariate Poisson Distributions . In AAAI , 2017 . A. Molina, S. Natarajan, and K. Kersting. Poisson Sum-Product Networks: A Deep Architecture for Tractable Multivariate Poisson Distributions. In AAAI, 2017."},{"key":"e_1_2_1_29_1","volume-title":"AAAI","author":"Molina A.","year":"2018","unstructured":"A. Molina , A. Vergari , N. D. Mauro , S. Natarajan , F. Esposito , and K. Kersting . Mixed Sum-Product Networks: A Deep Architecture for Hybrid Domains . In AAAI , 2018 . A. Molina, A. Vergari, N. D. Mauro, S. Natarajan, F. Esposito, and K. Kersting. Mixed Sum-Product Networks: A Deep Architecture for Hybrid Domains. In AAAI, 2018."},{"key":"e_1_2_1_30_1","volume-title":"Sp ow: An easy and extensible library for deep probabilistic learning using sum-product networks","author":"Molina A.","year":"2019","unstructured":"A. Molina , A. Vergari , K. Stelzner , R. Peharz , P. Subramani , N. D. Mauro , P. Poupart , and K. Kersting . Sp ow: An easy and extensible library for deep probabilistic learning using sum-product networks , 2019 . A. Molina, A. Vergari, K. Stelzner, R. Peharz, P. Subramani, N. D. Mauro, P. Poupart, and K. Kersting. Sp ow: An easy and extensible library for deep probabilistic learning using sum-product networks, 2019."},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2009.123"},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-10424-4_17"},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3183713.3196905"},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3035918.3064013"},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2011.6130310"},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/2213836.2213879"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-009-0153-2"},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/312129.312231"},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3329859.3329871"},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD.2018.00060"},{"key":"e_1_2_1_41_1","volume-title":"Oct. 12","author":"Suciu D.","year":"2010","unstructured":"D. Suciu and C. Re . Efficient top-k query evaluation on probabilistic data , Oct. 12 2010 . US Patent 7,814,113. D. Suciu and C. Re. Efficient top-k query evaluation on probabilistic data, Oct. 12 2010. US Patent 7,814,113."},{"key":"e_1_2_1_42_1","volume-title":"An end-to-end learning-based cost estimator. CoRR, abs\/1906.02560","author":"Sun J.","year":"2019","unstructured":"J. Sun and G. Li . An end-to-end learning-based cost estimator. CoRR, abs\/1906.02560 , 2019 . J. Sun and G. Li. An end-to-end learning-based cost estimator. CoRR, abs\/1906.02560, 2019."},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/1376616.1376696"},{"key":"e_1_2_1_44_1","volume-title":"Approximate query processing using deep generative models. CoRR, abs\/1903.10000","author":"Thirumuruganathan S.","year":"2019","unstructured":"S. Thirumuruganathan , S. Hasan , N. Koudas , and G. Das . Approximate query processing using deep generative models. CoRR, abs\/1903.10000 , 2019 . S. Thirumuruganathan, S. Hasan, N. Koudas, and G. Das. Approximate query processing using deep generative models. CoRR, abs\/1903.10000, 2019."},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-012-0293-7"},{"key":"e_1_2_1_46_1","volume-title":"Twenty-Ninth AAAI Conference on Artificial Intelligence","author":"Van den Broeck G.","year":"2015","unstructured":"G. Van den Broeck and A. Darwiche . On the role of canonicity in knowledge compilation . In Twenty-Ninth AAAI Conference on Artificial Intelligence , 2015 . G. Van den Broeck and A. Darwiche. On the role of canonicity in knowledge compilation. In Twenty-Ninth AAAI Conference on Artificial Intelligence, 2015."},{"key":"e_1_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.14778\/1453856.1453896"},{"key":"e_1_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3329859.3329875"},{"key":"e_1_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.14778\/3291264.3291267"},{"key":"e_1_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3299869.3319861"},{"key":"e_1_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.14778\/3368289.3368294"}],"container-title":["Proceedings of the VLDB Endowment"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.14778\/3384345.3384349","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,28]],"date-time":"2022-12-28T09:52:29Z","timestamp":1672221149000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.14778\/3384345.3384349"}},"subtitle":["learn from data, not from queries!"],"short-title":[],"issued":{"date-parts":[[2020,3]]},"references-count":51,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2020,3]]}},"alternative-id":["10.14778\/3384345.3384349"],"URL":"https:\/\/doi.org\/10.14778\/3384345.3384349","relation":{},"ISSN":["2150-8097"],"issn-type":[{"value":"2150-8097","type":"print"}],"subject":[],"published":{"date-parts":[[2020,3]]}}}