{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T11:05:36Z","timestamp":1779447936826,"version":"3.53.1"},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T00:00:00Z","timestamp":1773705600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T00:00:00Z","timestamp":1773705600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["The VLDB Journal"],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1007\/s00778-026-00970-y","type":"journal-article","created":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T18:53:24Z","timestamp":1773773604000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Lamba: A pretrained model for latency prediction over distributed databases"],"prefix":"10.1007","volume":"35","author":[{"given":"Yingli","family":"Zhou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianjing","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9976-9490","authenticated-orcid":false,"given":"Rong","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yingze","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junwei","family":"Lan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhewei","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yixiang","family":"Fang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bolin","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingren","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,3,17]]},"reference":[{"key":"970_CR1","unstructured":"(GCN Github repository) https:\/\/github.com\/DataManagementLab\/zero-shot-cost-estimation\/tree\/main"},{"key":"970_CR2","unstructured":"(IMDB Dataset) http:\/\/homepages.cwi.nl\/~boncz\/job\/imdb.tgz"},{"key":"970_CR3","unstructured":"(LAMBA Repository) https:\/\/drive.google.com\/file\/d\/1ip06XqrswKi64OSb-QDSC_kdjt6hB7_e\/view?usp=sharing"},{"key":"970_CR4","unstructured":"(Osprey Github repository) https:\/\/github.com\/parimarjan\/LatencyPredictor"},{"key":"970_CR5","unstructured":"(QueryFormer Github repository) https:\/\/github.com\/zhaoyue-ntu\/QueryFormer"},{"key":"970_CR6","unstructured":"(STATS Dataset) https:\/\/relational.fit.cvut.cz\/dataset\/Stats"},{"key":"970_CR7","unstructured":"(TCNN Github repository) https:\/\/github.com\/RyanMarcus\/TreeConvolution"},{"key":"970_CR8","unstructured":"(TPCH Dataset) https:\/\/www.tpc.org\/tpc_documents_current_versions\/current_specifications5.asp"},{"key":"970_CR9","unstructured":"Achiam J, Adler S, Agarwal S, Ahmad L, Akkaya I, Aleman FL, Almeida D, Altenschmidt J, Altman S, Anadkat S, et\u00a0al (2023) Gpt-4 technical report. arXiv preprint arXiv:2303.08774"},{"key":"970_CR10","doi-asserted-by":"crossref","unstructured":"Akdere M, \u00c7etintemel U, Riondato M, Upfal E, Zdonik SB (2012) Learning-based query performance modeling and prediction. In: 2012 IEEE 28th International Conference on Data Engineering, IEEE, pp 390\u2013401","DOI":"10.1109\/ICDE.2012.64"},{"key":"970_CR11","unstructured":"Bach FR, Jordan MI (2002) Kernel independent component analysis. Journal of machine learning research 3(Jul):1\u201348"},{"key":"970_CR12","first-page":"485","volume-title":"Google bigquery","author":"E Bisong","year":"2019","unstructured":"Bisong, E., Bisong, E.: Google bigquery, pp. 485\u2013517. A Comprehensive Guide for Beginners, Building Machine Learning and Deep Learning Models on Google Cloud Platform (2019)"},{"key":"970_CR13","doi-asserted-by":"crossref","unstructured":"Chandramouli, B., Goldstein, J., Barga, R., Riedewald, M., Santos, I.: Accurate latency estimation in a distributed event processing system. In: 2011 IEEE 27th International Conference on Data Engineering, IEEE, pp 255\u2013266 (2011)","DOI":"10.1109\/ICDE.2011.5767926"},{"key":"970_CR14","doi-asserted-by":"publisher","unstructured":"Chen, J., Ye, G., Zhao, Y., Liu, S., Deng, L., Chen, X., Zhou, R., Zheng, K.: Efficient join order selection learning with graph-based representation. In: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Association for Computing Machinery, New York, NY, USA, KDD \u201922, p 97\u2013107, https:\/\/doi.org\/10.1145\/3534678.3539303 (2022)","DOI":"10.1145\/3534678.3539303"},{"key":"970_CR15","doi-asserted-by":"crossref","unstructured":"Gupta A, Agarwal D, Tan D, Kulesza J, Pathak R, Stefani S, Srinivasan V (2015) Amazon redshift and the case for simpler data warehouses. In: Proceedings of the 2015 ACM SIGMOD international conference on management of data, pp 1917\u20131923","DOI":"10.1145\/2723372.2742795"},{"issue":"4","key":"970_CR16","doi-asserted-by":"publisher","first-page":"752","DOI":"10.14778\/3503585.3503586","volume":"15","author":"Y Han","year":"2021","unstructured":"Han, Y., Wu, Z., Wu, P., Zhu, R., Yang, J., Tan, L.W., Zeng, K., Cong, G., Qin, Y., Pfadler, A., Qian, Z., Zhou, J., Li, J., Cui, B.: Cardinality estimation in DBMS: A comprehensive benchmark evaluation. Proc VLDB Endow 15(4), 752\u2013765 (2021)","journal-title":"Proc VLDB Endow"},{"key":"970_CR17","doi-asserted-by":"crossref","unstructured":"Herodotou H, Borisov N, Babu S (2011) Query optimization techniques for partitioned tables. In: Proceedings of the 2011 ACM SIGMOD International Conference on Management of data, pp 49\u201360","DOI":"10.1145\/1989323.1989330"},{"issue":"11","key":"970_CR18","doi-asserted-by":"publisher","first-page":"2361","DOI":"10.14778\/3551793.3551799","volume":"15","author":"B Hilprecht","year":"2022","unstructured":"Hilprecht, B., Binnig, C.: Zero-shot cost models for out-of-the-box learned cost prediction. Proceedings of the VLDB Endowment 15(11), 2361\u20132374 (2022)","journal-title":"Proceedings of the VLDB Endowment"},{"key":"970_CR19","unstructured":"Hilprecht B, Binnig C (2022b) Zero-shot cost models for out-of-the-box learned cost prediction. CoRR abs\/2201.00561, arxiv:2201.00561"},{"key":"970_CR20","doi-asserted-by":"crossref","unstructured":"Huang S, Qin Y, Zhang X, Tu Y, Li Z, Cui B (2023) Survey on performance optimization for database systems. Science China Information Sciences 66(2):121,102","DOI":"10.1007\/s11432-021-3578-6"},{"key":"970_CR21","unstructured":"Kingma DP, Ba J (2015) Adam: A method for stochastic optimization. In: ICLR"},{"issue":"3","key":"970_CR22","doi-asserted-by":"publisher","first-page":"204","DOI":"10.14778\/2850583.2850594","volume":"9","author":"V Leis","year":"2015","unstructured":"Leis, V., Gubichev, A., Mirchev, A., Boncz, P., Kemper, A., Neumann, T.: How good are query optimizers, really? Proceedings of the VLDB Endowment 9(3), 204\u2013215 (2015)","journal-title":"Proceedings of the VLDB Endowment"},{"key":"970_CR23","doi-asserted-by":"crossref","unstructured":"Li Y, Wang L, Wang S, Sun Y, Peng Z (2022) A resource-aware deep cost model for big data query processing. In: 2022 IEEE 38th International Conference on Data Engineering (ICDE), IEEE, pp 885\u2013897","DOI":"10.1109\/ICDE53745.2022.00071"},{"key":"970_CR24","doi-asserted-by":"crossref","unstructured":"Liu F, Blanas S (2015) Forecasting the cost of processing multi-join queries via hashing for main-memory databases. In: Proceedings of the Sixth ACM Symposium on Cloud Computing, pp 153\u2013166","DOI":"10.1145\/2806777.2806944"},{"key":"970_CR25","unstructured":"L\u00f3pez-Paz D, Hennig P, Sch\u00f6lkopf B (2013) The randomized dependence coefficient. In: Burges CJC, Bottou L, Ghahramani Z, Weinberger KQ (eds) Advances in Neural Information Processing Systems 26: 27th Annual Conference on Neural Information Processing Systems 2013. Proceedings of a meeting held December 5-8, 2013, Lake Tahoe, Nevada, United States, pp 1\u20139, https:\/\/proceedings.neurips.cc\/paper\/2013\/hash\/aab3238922bcc25a6f606eb525ffdc56-Abstract.html"},{"issue":"3","key":"970_CR26","doi-asserted-by":"publisher","first-page":"414","DOI":"10.14778\/3494124.3494127","volume":"15","author":"Y Lu","year":"2021","unstructured":"Lu, Y., Kandula, S., K\u00f6nig, A.C., Chaudhuri, S.: Pre-training summarization models of structured datasets for cardinality estimation. Proceedings of the VLDB Endowment 15(3), 414\u2013426 (2021)","journal-title":"Proceedings of the VLDB Endowment"},{"key":"970_CR27","doi-asserted-by":"crossref","unstructured":"Lyu Z, Zhang HH, Xiong G, Guo G, Wang H, Chen J, Praveen A, Yang Y, Gao X, Wang A, et\u00a0al (2021) Greenplum: a hybrid database for transactional and analytical workloads. In: Proceedings of the 2021 International Conference on Management of Data, pp 2530\u20132542","DOI":"10.1145\/3448016.3457562"},{"key":"970_CR28","doi-asserted-by":"crossref","unstructured":"Ma L, Zhang W, Jiao J, Wang W, Butrovich M, Lim WS, Menon P, Pavlo A (2021) Mb2: decomposed behavior modeling for self-driving database management systems. In: Proceedings of the 2021 International Conference on Management of Data, pp 1248\u20131261","DOI":"10.1145\/3448016.3457276"},{"key":"970_CR29","doi-asserted-by":"crossref","unstructured":"Manegold S, Boncz P, Kersten ML (2002) Generic database cost models for hierarchical memory systems. In: VLDB\u201902: Proceedings of the 28th International Conference on Very Large Databases, Elsevier, pp 191\u2013202","DOI":"10.1016\/B978-155860869-6\/50025-1"},{"issue":"11","key":"970_CR30","doi-asserted-by":"publisher","first-page":"1733","DOI":"10.14778\/3342263.3342646","volume":"12","author":"R Marcus","year":"2019","unstructured":"Marcus, R., Papaemmanouil, O.: Plan-structured deep neural network models for query performance prediction. Proceedings of the VLDB Endowment 12(11), 1733\u20131746 (2019)","journal-title":"Proceedings of the VLDB Endowment"},{"issue":"11","key":"970_CR31","doi-asserted-by":"publisher","first-page":"1705","DOI":"10.14778\/3342263.3342644","volume":"12","author":"R Marcus","year":"2019","unstructured":"Marcus, R., Negi, P., Mao, H., Zhang, C., Alizadeh, M., Kraska, T., Papaemmanouil, O., Tatbul, N.: Neo: a learned query optimizer. Proceedings of the VLDB Endowment 12(11), 1705\u20131718 (2019)","journal-title":"Proceedings of the VLDB Endowment"},{"key":"970_CR32","doi-asserted-by":"publisher","unstructured":"Marcus R, Negi P, Mao H, Tatbul N, Alizadeh M, Kraska T (2021) Bao: Making learned query optimization practical. In: Proceedings of the 2021 International Conference on Management of Data, Association for Computing Machinery, New York, NY, USA, SIGMOD \u201921, p 1275\u20131288, https:\/\/doi.org\/10.1145\/3448016.3452838","DOI":"10.1145\/3448016.3452838"},{"issue":"3","key":"970_CR33","doi-asserted-by":"publisher","first-page":"1095","DOI":"10.1145\/1166074.1166084","volume":"31","author":"A Metwally","year":"2006","unstructured":"Metwally, A., Agrawal, D., Abbadi, A.E.: An integrated efficient solution for computing frequent and top-k elements in data streams. ACM Trans. Database Syst. 31(3), 1095\u20131133 (2006). https:\/\/doi.org\/10.1145\/1166074.1166084","journal-title":"ACM Trans. Database Syst."},{"issue":"1","key":"970_CR34","doi-asserted-by":"publisher","first-page":"982","DOI":"10.14778\/1687627.1687738","volume":"2","author":"G Moerkotte","year":"2009","unstructured":"Moerkotte, G., Neumann, T., Steidl, G.: Preventing bad plans by bounding the impact of cardinality estimation errors. Proc VLDB Endow 2(1), 982\u2013993 (2009)","journal-title":"Proc VLDB Endow"},{"key":"970_CR35","unstructured":"Negi P, Wu Z, Nasr-Esfahany A, Sharma H, Alizadeh M, Kraska T, Madden S (2024) Os pre-trained transformer: Predicting query latencies across changing system contexts"},{"key":"970_CR36","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1007\/978-3-642-10424-4_17","volume-title":"Performance Evaluation and Benchmarking","author":"P O\u2019Neil","year":"2009","unstructured":"O\u2019Neil, P., O\u2019Neil, E., Chen, X., Revilak, S.: The star schema benchmark and augmented fact table indexing. In: Nambiar, R., Poess, M. (eds.) Performance Evaluation and Benchmarking, pp. 237\u2013252. Springer, Berlin Heidelberg, Berlin, Heidelberg (2009)"},{"key":"970_CR37","doi-asserted-by":"publisher","unstructured":"O\u2019Neil PE, O\u2019Neil EJ, Chen X, Revilak S (2009b) The star schema benchmark and augmented fact table indexing. In: Nambiar RO, Poess M (eds) Performance Evaluation and Benchmarking, First TPC Technology Conference, TPCTC 2009, Lyon, France, August 24-28, 2009, Revised Selected Papers, Springer, Lecture Notes in Computer Science, vol 5895, pp 237\u2013252, https:\/\/doi.org\/10.1007\/978-3-642-10424-4_17","DOI":"10.1007\/978-3-642-10424-4_17"},{"issue":"4","key":"970_CR38","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1145\/369275.369291","volume":"29","author":"M Poess","year":"2000","unstructured":"Poess, M., Floyd, C.: New tpc benchmarks for decision support and web commerce. SIGMOD Rec 29(4), 64\u201371 (2000). https:\/\/doi.org\/10.1145\/369275.369291","journal-title":"SIGMOD Rec"},{"key":"970_CR39","doi-asserted-by":"publisher","unstructured":"Song Y, Li Y, Fan S, He D, Liao J (2022) A new graph neural network-based join optimization algorithm. In: 2022 International Conference on Algorithms, Data Mining, and Information Technology (ADMIT), pp 20\u201324, https:\/\/doi.org\/10.1109\/ADMIT57209.2022.00012","DOI":"10.1109\/ADMIT57209.2022.00012"},{"issue":"3","key":"970_CR40","doi-asserted-by":"publisher","first-page":"307","DOI":"10.14778\/3368289.3368296","volume":"13","author":"J Sun","year":"2019","unstructured":"Sun, J., Li, G.: An end-to-end learning-based cost estimator. Proceedings of the VLDB Endowment 13(3), 307\u2013319 (2019)","journal-title":"Proceedings of the VLDB Endowment"},{"key":"970_CR41","unstructured":"Vaswani A (2017) Attention is all you need. Advances in Neural Information Processing Systems"},{"key":"970_CR42","doi-asserted-by":"crossref","unstructured":"Wu W, Chi Y, Zhu S, Tatemura J, Hacig\u00fcm\u00fcs H, Naughton JF (2013) Predicting query execution time: Are optimizer cost models really unusable? In: 2013 IEEE 29th International Conference on Data Engineering (ICDE), IEEE, pp 1081\u20131092","DOI":"10.1109\/ICDE.2013.6544899"},{"issue":"14","key":"970_CR43","doi-asserted-by":"publisher","first-page":"1857","DOI":"10.14778\/2733085.2733092","volume":"7","author":"W Wu","year":"2014","unstructured":"Wu, W., Wu, X., Hacig\u00fcm\u00fc\u015f, H., Naughton, J.F.: Uncertainty aware query execution time prediction. Proceedings of the VLDB Endowment 7(14), 1857\u20131868 (2014)","journal-title":"Proceedings of the VLDB Endowment"},{"key":"970_CR44","doi-asserted-by":"crossref","unstructured":"Wu Z, Marcus R, Liu Z, Negi P, Nathan V, Pfeil P, Saxena G, Rahman M, Narayanaswamy B, Kraska T (2024) Stage: Query execution time prediction in amazon redshift. In: Companion of the 2024 International Conference on Management of Data, pp 280\u2013294","DOI":"10.1145\/3626246.3653391"},{"key":"970_CR45","doi-asserted-by":"publisher","unstructured":"Zeng T, Wei Z, Luo G, Yi K, Du X, Wen JR (2022) Persistent summaries. ACM Trans Database Syst 47(3), https:\/\/doi.org\/10.1145\/3531053","DOI":"10.1145\/3531053"},{"key":"970_CR46","doi-asserted-by":"crossref","unstructured":"Zeng T, Lan J, Ma J, Wei W, Zhu R, Li P, Ding B, Lian D, Wei Z, Zhou J (2024) Price: A pretrained model for cross-database cardinality estimation. arXiv preprint arXiv:2406.01027","DOI":"10.14778\/3712221.3712231"},{"issue":"12","key":"970_CR47","doi-asserted-by":"publisher","first-page":"2059","DOI":"10.14778\/3352063.3352124","volume":"12","author":"C Zhan","year":"2019","unstructured":"Zhan, C., Su, M., Wei, C., Peng, X., Lin, L., Wang, S., Chen, Z., Li, F., Pan, Y., Zheng, F., et al.: Analyticdb: real-time olap database system at alibaba cloud. Proceedings of the VLDB Endowment 12(12), 2059\u20132070 (2019)","journal-title":"Proceedings of the VLDB Endowment"},{"issue":"8","key":"970_CR48","doi-asserted-by":"publisher","first-page":"1658","DOI":"10.14778\/3529337.3529349","volume":"15","author":"Y Zhao","year":"2022","unstructured":"Zhao, Y., Cong, G., Shi, J., Miao, C.: Queryformer: A tree transformer model for query plan representation. Proceedings of the VLDB Endowment 15(8), 1658\u20131670 (2022)","journal-title":"Proceedings of the VLDB Endowment"},{"issue":"1","key":"970_CR49","first-page":"1","volume":"1","author":"X Zhou","year":"2023","unstructured":"Zhou, X., Li, G., Feng, J., Liu, L., Guo, W.: Grep: A graph learning based database partitioning system. Proceedings of the ACM on Management of Data 1(1), 1\u201324 (2023)","journal-title":"Proceedings of the ACM on Management of Data"}],"container-title":["The VLDB Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00778-026-00970-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00778-026-00970-y","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00778-026-00970-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T10:16:14Z","timestamp":1779444974000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00778-026-00970-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,17]]},"references-count":49,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,4]]}},"alternative-id":["970"],"URL":"https:\/\/doi.org\/10.1007\/s00778-026-00970-y","relation":{},"ISSN":["1066-8888","0949-877X"],"issn-type":[{"value":"1066-8888","type":"print"},{"value":"0949-877X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,17]]},"assertion":[{"value":"21 June 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 January 2026","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 February 2026","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 March 2026","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"18"}}