{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T09:00:49Z","timestamp":1775638849336,"version":"3.50.1"},"reference-count":47,"publisher":"Association for Computing Machinery (ACM)","issue":"3","funder":[{"DOI":"10.13039\/100018769","name":"DFKI","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100018769","id-type":"DOI","asserted-by":"crossref"}]},{"name":"LOEWE","award":["Reference III 5 - 519\/05.00.003-(0005)"],"award-info":[{"award-number":["Reference III 5 - 519\/05.00.003-(0005)"]}]},{"name":"hessian.AI"},{"DOI":"10.13039\/501100005714","name":"TU Darmstadt","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100005714","id-type":"DOI","asserted-by":"crossref"}]},{"name":"DHBW Mannheim"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Proc. ACM Manag. Data"],"published-print":{"date-parts":[[2025,6,17]]},"abstract":"<jats:p>\n                    Traditionally, query optimizers rely on cost models to choose the best execution plan from several candidates, making precise cost estimates critical for efficient query execution. In recent years, cost models based on machine learning have been proposed to overcome the weaknesses of traditional cost models. While these models have been shown to provide better prediction accuracy, only limited efforts have been made to investigate how well\n                    <jats:italic toggle=\"yes\">Learned Cost Models<\/jats:italic>\n                    (LCMs) actually perform in query optimization and how they affect overall query performance. In this paper, we address this by a systematic study evaluating LCMs on three of the core query optimization tasks:\n                    <jats:italic toggle=\"yes\">join ordering, access path selection,<\/jats:italic>\n                    and\n                    <jats:italic toggle=\"yes\">physical operator selection<\/jats:italic>\n                    . In our study, we compare seven state-of-the-art LCMs to a traditional cost model and, surprisingly, find that the traditional model often still outperforms LCMs in these tasks. We conclude by highlighting major takeaways and recommendations to guide future research toward making LCMs more effective for query optimization.\n                  <\/jats:p>","DOI":"10.1145\/3725309","type":"journal-article","created":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T21:23:29Z","timestamp":1750281809000},"page":"1-27","source":"Crossref","is-referenced-by-count":9,"title":["How Good are Learned Cost Models, Really? Insights from Query Optimization Tasks"],"prefix":"10.1145","volume":"3","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7321-9562","authenticated-orcid":false,"given":"Roman","family":"Heinrich","sequence":"first","affiliation":[{"name":"Technical University of Darmstadt, Darmstadt, Germany and DFKI Darmstadt, Darmstadt, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3788-6664","authenticated-orcid":false,"given":"Manisha","family":"Luthra","sequence":"additional","affiliation":[{"name":"Technical University of Darmstadt, Darmstadt, Germany and DFKI Darmstadt, Darmstadt, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7152-8959","authenticated-orcid":false,"given":"Johannes","family":"Wehrstein","sequence":"additional","affiliation":[{"name":"Technical University of Darmstadt, Darmstadt, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8878-7623","authenticated-orcid":false,"given":"Harald","family":"Kornmayer","sequence":"additional","affiliation":[{"name":"Duale Hochschule Baden-W\u00fcrttemberg (DHBW) Mannheim, Mannheim, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2744-7836","authenticated-orcid":false,"given":"Carsten","family":"Binnig","sequence":"additional","affiliation":[{"name":"Technical University of Darmstadt, Darmstadt, Germany and DFKI Darmstadt, Darmstadt, Germany"}]}],"member":"320","published-online":{"date-parts":[[2025,6,18]]},"reference":[{"key":"e_1_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE60146.2024.00163"},{"key":"e_1_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2012.64"},{"key":"e_1_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/320455.320457"},{"key":"e_1_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.18420\/BTW2023--25"},{"key":"e_1_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978--3-031--68323--7_25"},{"key":"e_1_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.14778\/3598581.3598597"},{"key":"e_1_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3588963"},{"key":"e_1_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/1989323.1989359"},{"key":"e_1_2_2_9_1","volume-title":"Proceedings of the 2019 USENIX Annual Technical Conference, USENIX ATC 2019","author":"Duplyakin Dmitry","year":"2019","unstructured":"Dmitry Duplyakin, Robert Ricci, Aleksander Maricq, Gary Wong, Jonathon Duerig, Eric Eide, Leigh Stoller, Mike Hibler, David Johnson, Kirk Webb, Aditya Akella, Kuang-Ching Wang, Glenn Ricart, Larry Landweber, Chip Elliott, Michael Zink, Emmanuel Cecchet, Snigdhaswin Kar, and Prabodh Mishra. 2019. The Design and Operation of CloudLab. In Proceedings of the 2019 USENIX Annual Technical Conference, USENIX ATC 2019, Renton, WA, USA, July 10--12, 2019, Dahlia Malkhi and Dan Tsafrir (Eds.). USENIX Association, 1--14. https:\/\/www.usenix.org\/conference\/atc19\/presentation\/duplyakin"},{"key":"e_1_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2009.130"},{"key":"e_1_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/1093382.1093387"},{"key":"e_1_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE60146.2024.00015"},{"key":"e_1_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.14778\/3551793.3551799"},{"key":"e_1_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.14778\/3384345.3384349"},{"key":"e_1_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2668260.2668271"},{"key":"e_1_2_2_16_1","volume-title":"LightGBM: A Highly Efficient Gradient Boosting Decision Tree. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017","author":"Ke Guolin","year":"2017","unstructured":"Guolin Ke, Qi Meng, Thomas Finley, Taifeng Wang, Wei Chen, Weidong Ma, Qiwei Ye, and Tie-Yan Liu. 2017. LightGBM: A Highly Efficient Gradient Boosting Decision Tree. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4--9, 2017, Long Beach, CA, USA, Isabelle Guyon, Ulrike von Luxburg, Samy Bengio, Hanna M. Wallach, Rob Fergus, S. V. N. Vishwanathan, and Roman Garnett (Eds.). 3146--3154. https:\/\/proceedings.neurips.cc\/paper\/2017\/hash\/6449f44a102fde848669bdd9eb6b76fa-Abstract.html"},{"key":"e_1_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3514221.3526154"},{"key":"e_1_2_2_18_1","volume-title":"Learned Cardinalities: Estimating Correlated Joins with Deep Learning. In 9th Biennial Conference on Innovative Data Systems Research, CIDR","author":"Kipf Andreas","year":"2019","unstructured":"Andreas Kipf, Thomas Kipf, Bernhard Radke, Viktor Leis, Peter A. Boncz, and Alfons Kemper. 2019. 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. www.cidrdb.org. http:\/\/cidrdb.org\/cidr2019\/papers\/p101-kipf-cidr19.pdf"},{"key":"e_1_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/S41019-020-00149--7"},{"key":"e_1_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.14778\/3654621.3654625"},{"key":"e_1_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.14778\/2850583.2850594"},{"key":"e_1_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/J.INS.2024.120650"},{"key":"e_1_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE60146.2024.00374"},{"key":"e_1_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557305"},{"key":"e_1_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.14778\/3494124.3494127"},{"key":"e_1_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3542700.3542703"},{"key":"e_1_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.14778\/3342263.3342646"},{"key":"e_1_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.14778\/3636218.3636229"},{"key":"e_1_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/582095.582099"},{"key":"e_1_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.2307\/1412159"},{"key":"e_1_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.14778\/3368289.3368296"},{"key":"e_1_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.14778\/3485450.3485459"},{"key":"e_1_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.14778\/3681954.3682031"},{"key":"e_1_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.14778\/3583140.3583156"},{"key":"e_1_2_2_35_1","volume-title":"Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017","author":"Vaswani Ashish","year":"2017","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 30: Annual Conference on Neural Information Processing Systems 2017, December 4--9, 2017, Long Beach, CA, USA, Isabelle Guyon, Ulrike von Luxburg, Samy Bengio, Hanna M. Wallach, Rob Fergus, S. V. N. Vishwanathan, and Roman Garnett (Eds.). 5998--6008. https:\/\/proceedings.neurips.cc\/paper\/2017\/hash\/3f5ee243547dee91fbd053c1c4a845aa-Abstract.html"},{"key":"e_1_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.14778\/3461535.3461552"},{"key":"e_1_2_2_37_1","volume-title":"Mysql Reference Manual","author":"Widenius Michael","unstructured":"Michael Widenius, Davis Axmark, and Paul DuBois. 2002. Mysql Reference Manual 1st ed.). O'Reilly & Associates, Inc., USA.","edition":"1"},{"key":"e_1_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2013.6544899"},{"key":"e_1_2_2_39_1","volume-title":"12th Conference on Innovative Data Systems Research, CIDR 2022","author":"Wu Ziniu","year":"2022","unstructured":"Ziniu Wu, Pei Yu, Peilun Yang, Rong Zhu, Yuxing Han, Yaliang Li, Defu Lian, Kai Zeng, and Jingren Zhou. 2022. A Unified Transferable Model for ML-Enhanced DBMS. In 12th Conference on Innovative Data Systems Research, CIDR 2022, Chaminade, CA, USA, January 9--12, 2022. www.cidrdb.org. https:\/\/www.cidrdb.org\/cidr2022\/papers\/p6-wu.pdf"},{"key":"e_1_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626769"},{"key":"e_1_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3514221.3517885"},{"key":"e_1_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.14778\/3421424.3421432"},{"key":"e_1_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.14778\/3368289.3368294"},{"key":"e_1_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.14778\/3529337.3529349"},{"key":"e_1_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.14778\/3636218.3636235"},{"key":"e_1_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.14778\/3397230.3397238"},{"key":"e_1_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.14778\/3583140.3583160"}],"container-title":["Proceedings of the ACM on Management of Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3725309","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T18:57:02Z","timestamp":1774983422000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3725309"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,17]]},"references-count":47,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2025,6,17]]}},"alternative-id":["10.1145\/3725309"],"URL":"https:\/\/doi.org\/10.1145\/3725309","relation":{},"ISSN":["2836-6573"],"issn-type":[{"value":"2836-6573","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,17]]}}}