{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T20:52:42Z","timestamp":1775595162819,"version":"3.50.1"},"reference-count":48,"publisher":"Association for Computing Machinery (ACM)","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Proc. ACM Manag. Data"],"published-print":{"date-parts":[[2026,4,2]]},"abstract":"<jats:p>\n                    Although machine learning (ML) shows potential in improving query optimization by generating and selecting more efficient plans, ensuring the robustness of learning-based cost models (LCMs) remains challenging. These LCMs currently lack explainability, which undermines user trust and limits the ability to derive insights from their cost predictions to improve plan quality. Accurately converting tree-structured query plans into representations via tree models is also essential, as omitting any details may negatively impact subsequent cost model performance. Additionally, inherent uncertainty in cost estimation leads to inaccurate predictions, resulting in suboptimal plan selection. To address these challenges, we introduce Reqo, a\n                    <jats:underline>R<\/jats:underline>\n                    obust and\n                    <jats:underline>E<\/jats:underline>\n                    xplainable\n                    <jats:underline>Q<\/jats:underline>\n                    uery\n                    <jats:underline>O<\/jats:underline>\n                    ptimization cost model that comprehensively enhances three main stages in query optimization: plan generation, plan representation, and plan selection. Reqo integrates three innovations: the first explainability technique for LCMs that quantifies subgraph contributions and produces plan generation hints to enhance candidate plan quality; a novel tree model based on Bidirectional Graph Neural Networks (Bi-GNNs) with a Gated Recurrent Unit (GRU) aggregator to further capture both node-level and structural information and effectively strengthen plan representation; and an uncertainty-aware learning-to-rank cost estimator that adaptively integrates cost estimates with uncertainties to enhance plan selection robustness. Extensive experiments demonstrate that Reqo outperforms state-of-the-art approaches across all three stages.\n                  <\/jats:p>","DOI":"10.1145\/3786689","type":"journal-article","created":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T17:54:13Z","timestamp":1775584453000},"page":"1-27","source":"Crossref","is-referenced-by-count":0,"title":["Reqo: A Comprehensive Learning-Based Cost Model for Robust and Explainable Query Optimization"],"prefix":"10.1145","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-7414-3631","authenticated-orcid":false,"given":"Baoming","family":"Chang","sequence":"first","affiliation":[{"name":"University of Ottawa, Ottawa, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2176-4088","authenticated-orcid":false,"given":"Amin","family":"Kamali","sequence":"additional","affiliation":[{"name":"University of Ottawa, Ottawa, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3586-9406","authenticated-orcid":false,"given":"Verena","family":"Kantere","sequence":"additional","affiliation":[{"name":"University of Ottawa, Ottawa, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,4,7]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.14778\/3611540.3611544"},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1435"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-68323-7_25"},{"key":"e_1_2_1_4_1","volume-title":"An empirical evaluation of thompson sampling. Advances in neural information processing systems","author":"Chapelle Olivier","year":"2011","unstructured":"Olivier Chapelle and Lihong Li. 2011. An empirical evaluation of thompson sampling. Advances in neural information processing systems, Vol. 24 (2011)."},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.14778\/3598581.3598597"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.14778\/3484224.3484234"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3588963"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/2588555.2588566"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.14778\/3503585.3503586"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3725309"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.14778\/3551793.3551799"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.14778\/3742728.3742753"},{"key":"e_1_2_1_14_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_2_1_15_1","volume-title":"Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907","author":"Kipf Thomas N","year":"2016","unstructured":"Thomas N Kipf and Max Welling. 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)."},{"key":"e_1_2_1_16_1","volume-title":"Estimating mutual information. Physical Review E\u2014Statistical, Nonlinear, and Soft Matter Physics","author":"Kraskov Alexander","year":"2004","unstructured":"Alexander Kraskov, Harald St\u00f6gbauer, and Peter Grassberger. 2004. Estimating mutual information. Physical Review E\u2014Statistical, Nonlinear, and Soft Matter Physics, Vol. 69, 6 (2004), 066138."},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.14778\/2850583.2850594"},{"key":"e_1_2_1_18_1","volume-title":"Tune: A Research Platform for Distributed Model Selection and Training. arXiv preprint arXiv:1807.05118","author":"Liaw Richard","year":"2018","unstructured":"Richard Liaw, Eric Liang, Robert Nishihara, Philipp Moritz, Joseph E Gonzalez, and Ion Stoica. 2018. Tune: A Research Platform for Distributed Model Selection and Training. arXiv preprint arXiv:1807.05118 (2018)."},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3236386.3241340"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.14778\/3476249.3476254"},{"key":"e_1_2_1_21_1","article-title":"A simple approach to improve single-model deep uncertainty via distance-awareness","volume":"24","author":"Liu Jeremiah Zhe","year":"2023","unstructured":"Jeremiah Zhe Liu, Shreyas Padhy, Jie Ren, Zi Lin, Yeming Wen, Ghassen Jerfel, Zachary Nado, Jasper Snoek, Dustin Tran, and Balaji Lakshminarayanan. 2023. A simple approach to improve single-model deep uncertainty via distance-awareness. Journal of Machine Learning Research, Vol. 24, 1, Article 42 (Jan. 2023), 63 pages.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557305"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3448016.3452838"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.14778\/3342263.3342644"},{"key":"e_1_2_1_25_1","volume-title":"Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781","author":"Mikolov Tomas","year":"2013","unstructured":"Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013. Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781 (2013)."},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.14778\/1687627.1687738"},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.5555\/3015812.3016002"},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.14778\/3476249.3476259"},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICNN.1994.374138"},{"key":"e_1_2_1_30_1","volume-title":"Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al., 2019. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_2_1_31_1","unstructured":"pg_hint_plan Development Team. 2024. pg_hint_plan: PostgreSQL query-plan hinting extension. https:\/\/github.com\/ossc-db\/pg_hint_plan"},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/369275.369291"},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.5555\/1325851.1325979"},{"key":"e_1_2_1_34_1","first-page":"25","article-title":"Edge directionality improves learning on heterophilic graphs. In Learning on graphs conference","author":"Rossi Emanuele","year":"2024","unstructured":"Emanuele Rossi, Bertrand Charpentier, Francesco Di Giovanni, Fabrizio Frasca, Stephan G\u00fcnnemann, and Michael M Bronstein. 2024. Edge directionality improves learning on heterophilic graphs. In Learning on graphs conference. PMLR, 25-1.","journal-title":"PMLR"},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/214"},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.14778\/3368289.3368296"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1150"},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"e_1_2_1_39_1","unstructured":"Oleksii Vasyliev. 2014. PGTune: Tuning PostgreSQL configuration by hardware. https:\/\/github.com\/le0pard\/pgtune"},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.14778\/3611479.3611528"},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.14778\/3565838.3565846"},{"key":"e_1_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE48307.2020.00116"},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE48307.2020.00133"},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3514221.3526156"},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3514221.3526156"},{"key":"e_1_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.14778\/3529337.3529349"},{"key":"e_1_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.14778\/3583140.3583160"},{"key":"e_1_2_1_48_1","volume-title":"HERO: Hint-Based Efficient and Reliable Query Optimizer. arXiv preprint arXiv:2412.02372","author":"Zinchenko Sergey","year":"2024","unstructured":"Sergey Zinchenko and Sergey Iazov. 2024. HERO: Hint-Based Efficient and Reliable Query Optimizer. arXiv preprint arXiv:2412.02372 (2024)."}],"container-title":["Proceedings of the ACM on Management of Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3786689","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T19:56:12Z","timestamp":1775591772000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3786689"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,2]]},"references-count":48,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,4,2]]}},"alternative-id":["10.1145\/3786689"],"URL":"https:\/\/doi.org\/10.1145\/3786689","relation":{},"ISSN":["2836-6573"],"issn-type":[{"value":"2836-6573","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,2]]}}}