{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T06:33:49Z","timestamp":1790750029167,"version":"4.1.0"},"reference-count":40,"publisher":"Association for Computing Machinery (ACM)","issue":"6","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No.92270202, No.U22B2020"],"award-info":[{"award-number":["No.92270202, No.U22B2020"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Proc. ACM Manag. Data"],"published-print":{"date-parts":[[2025,12,4]]},"abstract":"<jats:p>Previous learning-based parameter query optimization (PQO) methods excel in static workloads by precisely selecting optimal plans in a cache with a fixed set of representative plans. However, these methods struggle in dynamic workloads because they cannot predict over dynamically changed plan caches. These queries that fall outside the previously observed query parameter distribution have the risk of reusing suboptimal plans.<\/jats:p>\n                  <jats:p>\n                    Unlike traditional PQO methods that learn mappings from parametric query parameters to a fixed set of execution plans, our adaptive PQO framework (\n                    <jats:italic toggle=\"yes\">APQO<\/jats:italic>\n                    ) takes both query parameters and the plans themselves as model inputs, thereby handling variable numbers of plans in dynamic workloads. By embedding plan representations through representation learning, we pre-train a foundation model offline, enabling\n                    <jats:italic toggle=\"yes\">APQO<\/jats:italic>\n                    to acquire a generalizable plan performance prediction model. Leveraging the foundation model's predictive capability along with a hybrid data augmentation strategy, we train an online calibration model with minimal training data for distribution-shifted new queries, rapidly adapting knowledge for reusing new plans.\n                  <\/jats:p>\n                  <jats:p>\n                    <jats:italic toggle=\"yes\">APQO<\/jats:italic>\n                    is natively designed to handle the characteristics of dynamic workloads. Experimental results show that\n                    <jats:italic toggle=\"yes\">APQO<\/jats:italic>\n                    outperforms existing PQO methods in dynamic workloads, achieving a higher cache hit ratio and significantly reducing query latency.\n                  <\/jats:p>","DOI":"10.1145\/3769761","type":"journal-article","created":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T04:32:13Z","timestamp":1764995533000},"page":"1-25","source":"Crossref","is-referenced-by-count":3,"title":["APQO: An Adaptive Framework for Parametric Query Optimization"],"prefix":"10.1145","volume":"3","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-4756-3635","authenticated-orcid":false,"given":"Sijia","family":"Li","sequence":"first","affiliation":[{"name":"East China Normal University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-7468-7695","authenticated-orcid":false,"given":"Peng","family":"Cai","sequence":"additional","affiliation":[{"name":"East China Normal University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4687-8927","authenticated-orcid":false,"given":"Zhifan","family":"Zhang","sequence":"additional","affiliation":[{"name":"East China Normal University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5220-3166","authenticated-orcid":false,"given":"Huiqi","family":"Hu","sequence":"additional","affiliation":[{"name":"East China Normal University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4610-4369","authenticated-orcid":false,"given":"Rong","family":"Zhang","sequence":"additional","affiliation":[{"name":"East China Normal University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8426-9450","authenticated-orcid":false,"given":"Xuan","family":"Zhou","sequence":"additional","affiliation":[{"name":"East China Normal University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8989-9662","authenticated-orcid":false,"given":"Quanqing","family":"Xu","sequence":"additional","affiliation":[{"name":"OceanBase, AntGroup, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3530-6476","authenticated-orcid":false,"given":"Chuanhui","family":"Yang","sequence":"additional","affiliation":[{"name":"OceanBase, AntGroup, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,12,5]]},"reference":[{"key":"e_1_2_1_1_1","unstructured":"[n.d.]. How the Planner Uses Statistics. https:\/\/www.postgresql.org\/docs\/8.1\/planner-stats-details.html"},{"key":"e_1_2_1_2_1","first-page":"402","article-title":"Parametric plan caching using density-based clustering","author":"Alu\u00e7 Gunes","year":"2012","unstructured":"Gunes Alu\u00e7, David E DeHaan, and Ivan T Bowman. 2012. Parametric plan caching using density-based clustering. In ICDE. 402-413.","journal-title":"ICDE."},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2008.160"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/1807167.1807226"},{"key":"e_1_2_1_5_1","volume-title":"Siamese neural networks: An overview. Artificial neural networks","author":"Chicco Davide","year":"2021","unstructured":"Davide Chicco. 2021. Siamese neural networks: An overview. Artificial neural networks (2021), 73-94."},{"key":"e_1_2_1_6_1","first-page":"1241","article-title":"Ai meets ai: Leveraging query executions to improve index recommendations","author":"Ding Bailu","year":"2019","unstructured":"Bailu Ding, Sudipto Das, Ryan Marcus, Wentao Wu, Surajit Chaudhuri, and Vivek R Narasayya. 2019. Ai meets ai: Leveraging query executions to improve index recommendations. In SIGMOD. 1241-1258.","journal-title":"SIGMOD."},{"key":"e_1_2_1_7_1","first-page":"1081","article-title":"On the Production of Anorexic Plan Diagrams","author":"Doraiswamy Harish","year":"2007","unstructured":"Harish Doraiswamy, Pooja N. Darera, and Jayant R. Haritsa. 2007. On the Production of Anorexic Plan Diagrams. In VLDB. 1081-1092.","journal-title":"VLDB."},{"key":"e_1_2_1_8_1","volume-title":"Kepler: Robust Learning for Parametric Query Optimization. SIGMOD","author":"Doshi Lyric","year":"2023","unstructured":"Lyric Doshi, Vincent Zhuang, Gaurav Jain, Ryan Marcus, Haoyu Huang, Deniz Altinb\u00fcken, Eugene Brevdo, and Campbell Fraser. 2023. Kepler: Robust Learning for Parametric Query Optimization. SIGMOD (2023), 1-25."},{"key":"e_1_2_1_9_1","first-page":"1539","article-title":"Leveraging re-costing for online optimization of parameterized queries with guarantees","author":"Dutt Anshuman","year":"2017","unstructured":"Anshuman Dutt, Vivek Narasayya, and Surajit Chaudhuri. 2017. Leveraging re-costing for online optimization of parameterized queries with guarantees. In SIGMOD. 1539-1554.","journal-title":"SIGMOD."},{"key":"e_1_2_1_10_1","first-page":"228","article-title":"Design and analysis of parametric query optimization algorithms","volume":"98","author":"Ganguly Sumit","year":"1998","unstructured":"Sumit Ganguly. 1998. Design and analysis of parametric query optimization algorithms. In VLDB, Vol. 98. 228-238.","journal-title":"VLDB"},{"key":"e_1_2_1_11_1","volume-title":"Kai Zeng, Gao Cong, Yanzhao Qin, Andreas Pfadler, Zhengping Qian, Jingren Zhou, Jiangneng Li, and Bin Cui.","author":"Han Yuxing","year":"2021","unstructured":"Yuxing Han, Ziniu Wu, Peizhi Wu, Rong Zhu, Jingyi Yang, Liang Wei Tan, Kai Zeng, Gao Cong, Yanzhao Qin, Andreas Pfadler, Zhengping Qian, Jingren Zhou, Jiangneng Li, and Bin Cui. 2021. Cardinality Estimation in DBMS: A Comprehensive Benchmark Evaluation. VLDB (2021), 752-765."},{"key":"e_1_2_1_12_1","first-page":"1228","article-title":"Analyzing plan diagrams of database query optimizers","author":"Haritsa Naveen Reddy","year":"2005","unstructured":"Naveen Reddy Jayant R Haritsa. 2005. Analyzing plan diagrams of database query optimizers. In VLDB. 1228-1239.","journal-title":"VLDB."},{"key":"e_1_2_1_13_1","first-page":"4834","article-title":"A twofold siamese network for real-time object tracking","author":"He Anfeng","year":"2018","unstructured":"Anfeng He, Chong Luo, Xinmei Tian, andWenjun Zeng. 2018. A twofold siamese network for real-time object tracking. In CVPR. 4834-4843.","journal-title":"CVPR."},{"key":"e_1_2_1_14_1","first-page":"167","article-title":"Parametric query optimization for linear and piecewise linear cost functions","author":"Hulgeri Arvind","year":"2002","unstructured":"Arvind Hulgeri and S Sudarshan. 2002. Parametric query optimization for linear and piecewise linear cost functions. In VLDB. 167-178.","journal-title":"VLDB."},{"key":"e_1_2_1_15_1","first-page":"766","article-title":"AniPQO: Almost non-intrusive parametric query optimization for nonlinear cost functions","author":"Hulgeri Arvind","year":"2003","unstructured":"Arvind Hulgeri and S Sudarshan. 2003. AniPQO: Almost non-intrusive parametric query optimization for nonlinear cost functions. In VLDB. 766-777.","journal-title":"VLDB."},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/234313.234367"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/s007780050037"},{"key":"e_1_2_1_18_1","first-page":"25","article-title":"Identifying robust plans through plan diagram reduction","volume":"24","author":"Darera Jayant Harish D","year":"2008","unstructured":"Harish D Pooja N Darera Jayant and R Haritsa. 2008. Identifying robust plans through plan diagram reduction. In VLDB, Vol. 24. 25.","journal-title":"VLDB"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.14778\/2850583.2850594"},{"key":"e_1_2_1_20_1","first-page":"2859","article-title":"AI meets database: AI4DB and DB4AI","author":"Li Guoliang","year":"2021","unstructured":"Guoliang Li, Xuanhe Zhou, and Lei Cao. 2021. AI meets database: AI4DB and DB4AI. In SIGMOD. 2859-2866.","journal-title":"SIGMOD."},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.14778\/3681954.3682030"},{"key":"e_1_2_1_22_1","first-page":"1275","article-title":"Bao: Making learned query optimization practical","author":"Marcus Ryan","year":"2021","unstructured":"Ryan Marcus, Parimarjan Negi, Hongzi Mao, Nesime Tatbul, Mohammad Alizadeh, and Tim Kraska. 2021. Bao: Making learned query optimization practical. In SIGMOD. 1275-1288.","journal-title":"SIGMOD."},{"key":"e_1_2_1_23_1","volume-title":"Plan-Structured Deep Neural Network Models for Query Performance Prediction. VLDB","author":"Marcus Ryan","year":"2019","unstructured":"Ryan Marcus and Olga Papaemmanouil. 2019. Plan-Structured Deep Neural Network Models for Query Performance Prediction. VLDB (2019), 1733-1746."},{"key":"e_1_2_1_24_1","unstructured":"Tomas Mikolov Kai Chen Greg Corrado and Jeffrey Dean. 2013. Efficient Estimation of Word Representations in Vector Space. arXiv:1301.3781 [cs.CL] https:\/\/arxiv.org\/abs\/1301.3781"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.14778\/3712221.3712248"},{"key":"e_1_2_1_26_1","unstructured":"Guna Prasaad. 2023. Skewed Data Generator for TPC-H:. https:\/\/github.com\/gunaprsd\/SkewedDataGenerator original-date: 2017-05-11T06:41:19Z."},{"key":"e_1_2_1_27_1","unstructured":"Greg Rahn. 2025. gregrahn\/join-order-benchmark. https:\/\/github.com\/gregrahn\/join-order-benchmark original-date: 2016-08-31T05:26:16Z."},{"key":"e_1_2_1_28_1","first-page":"1306","article-title":"St-siamesenet: Spatio-temporal siamese networks for human mobility signature identification","author":"Ren Huimin","year":"2020","unstructured":"Huimin Ren, Menghai Pan, Yanhua Li, Xun Zhou, and Jun Luo. 2020. St-siamesenet: Spatio-temporal siamese networks for human mobility signature identification. In SIGKDD. 1306-1315.","journal-title":"SIGKDD."},{"key":"e_1_2_1_29_1","unstructured":"A. Silberschatz H.F. Korth and S. Sudarshan. 2019. Database System Concepts. McGraw-Hill Education. https:\/\/dbbook.com\/"},{"key":"e_1_2_1_30_1","volume-title":"An End-to-End Learning-based Cost Estimator. VLDB","author":"Sun Ji","year":"2019","unstructured":"Ji Sun and Guoliang Li. 2019. An End-to-End Learning-based Cost Estimator. VLDB (2019), 307-319."},{"key":"e_1_2_1_31_1","first-page":"401","article-title":"Leveraging query logs and machine learning for parametric query optimization","volume":"15","author":"Vaidya Kapil","year":"2021","unstructured":"Kapil Vaidya, Anshuman Dutt, Vivek Narasayya, and Surajit Chaudhuri. 2021. Leveraging query logs and machine learning for parametric query optimization. VLDB 15, 3 (2021), 401-413.","journal-title":"VLDB"},{"key":"e_1_2_1_32_1","unstructured":"WilliamDAssafMSFT. 2024. Parameter Sensitive Plan optimization - SQL Server. https:\/\/learn.microsoft.com\/enus\/sql\/relational-databases\/performance\/parameter-sensitive-plan-optimization?view=sql-server-ver16"},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.14778\/3704965.3704971"},{"key":"e_1_2_1_34_1","first-page":"3882","article-title":"Join Order Selection with Deep Reinforcement Learning: Fundamentals, Techniques, and Challenges","volume":"16","author":"Yan Zhengtong","year":"2023","unstructured":"Zhengtong Yan, Valter Uotila, and Jiaheng Lu. 2023. Join Order Selection with Deep Reinforcement Learning: Fundamentals, Techniques, and Challenges. VLDB 16, 12 (2023), 3882-3885.","journal-title":"VLDB"},{"key":"e_1_2_1_35_1","first-page":"931","article-title":"Balsa: Learning a Query Optimizer Without Expert Demonstrations","author":"Yang Zongheng","year":"2022","unstructured":"Zongheng Yang, Wei-Lin Chiang, Sifei Luan, Gautam Mittal, Michael Luo, and Ion Stoica. 2022. Balsa: Learning a Query Optimizer Without Expert Demonstrations. In SIGMOD. 931-944.","journal-title":"SIGMOD."},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.14778\/3554821.3554830"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.14778\/3529337.3529349"},{"key":"e_1_2_1_38_1","first-page":"1014","article-title":"Efficient deep learning pipelines for accurate cost estimations over large scale query workload","author":"Zhi Kang Johan Kok","year":"2021","unstructured":"Johan Kok Zhi Kang, Gaurav, Sien Yi Tan, Feng Cheng, Shixuan Sun, and Bingsheng He. 2021. Efficient deep learning pipelines for accurate cost estimations over large scale query workload. In SIGMOD. 1014-1022.","journal-title":"SIGMOD."},{"key":"e_1_2_1_39_1","volume-title":"Query performance prediction for concurrent queries using graph embedding. 13","author":"Zhou Xuanhe","year":"2020","unstructured":"Xuanhe Zhou, Ji Sun, Guoliang Li, and Jianhua Feng. 2020. Query performance prediction for concurrent queries using graph embedding. 13 (2020), 1416-1428."},{"key":"e_1_2_1_40_1","first-page":"1416","article-title":"Query performance prediction for concurrent queries using graph embedding","volume":"13","author":"Zhou Xuanhe","year":"2020","unstructured":"Xuanhe Zhou, Ji Sun, Guoliang Li, and Jianhua Feng. 2020. Query performance prediction for concurrent queries using graph embedding. VLDB 13, 9 (2020), 1416-1428.","journal-title":"VLDB"}],"container-title":["Proceedings of the ACM on Management of Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3769761","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T04:40:29Z","timestamp":1781325629000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3769761"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,4]]},"references-count":40,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,12,4]]}},"alternative-id":["10.1145\/3769761"],"URL":"https:\/\/doi.org\/10.1145\/3769761","relation":{},"ISSN":["2836-6573"],"issn-type":[{"value":"2836-6573","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,4]]}}}