{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T13:51:53Z","timestamp":1781877113739,"version":"3.54.5"},"publisher-location":"Singapore","reference-count":27,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819538263","type":"print"},{"value":"9789819538270","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-981-95-3827-0_15","type":"book-chapter","created":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T13:03:42Z","timestamp":1781874222000},"page":"230-246","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ExBoost: Out-of-Box Co-optimization of\u00a0Machine Learning and\u00a0Join Queries"],"prefix":"10.1007","author":[{"given":"Kanchan","family":"Chowdhury","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lulu","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lixi","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jia","family":"Zou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,20]]},"reference":[{"key":"15_CR1","unstructured":"Nyc education (2000). https:\/\/geodacenter.github.io\/data-and-lab\/NYC-Census-2000\/. Accessed 10 Mar 2024"},{"key":"15_CR2","unstructured":"Block-level earnings in nyc (2002-14) (2014). https:\/\/geodacenter.github.io\/data-and-lab\/LEHD_Data\/. Accessed 05 Feb 2022"},{"key":"15_CR3","unstructured":"Pypi libpg query. PyPI (2017). https:\/\/pypi.org\/project\/pg_query\/0.16\/"},{"key":"15_CR4","doi-asserted-by":"crossref","unstructured":"de\u00a0Amorim, L.B., Cavalcanti, G.D., Cruz, R.M.: The choice of scaling technique matters for classification performance. Appl. Soft Comput. 133(C) (2023)","DOI":"10.1016\/j.asoc.2022.109924"},{"key":"15_CR5","unstructured":"Bai, J., Lu, F., Zhang, K., et\u00a0al.: ONNX: open neural network exchange (2019). https:\/\/github.com\/onnx\/onnx"},{"issue":"3","key":"15_CR6","first-page":"3","volume":"18","author":"S Chaudhuri","year":"1995","unstructured":"Chaudhuri, S., Shim, K.: An overview of cost-based optimization of queries with aggregates. IEEE Data Eng. Bull. 18(3), 3\u20139 (1995)","journal-title":"IEEE Data Eng. Bull."},{"key":"15_CR7","doi-asserted-by":"publisher","unstructured":"Chen, L., Kumar, A., Naughton, J., Patel, J.M.: Towards linear algebra over normalized data. Proc. VLDB Endow. 10(11), 1214\u20131225 (2017). https:\/\/doi.org\/10.14778\/3137628.3137633","DOI":"10.14778\/3137628.3137633"},{"key":"15_CR8","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. ICML\u201920, JMLR.org (2020)"},{"key":"15_CR9","unstructured":"developers, E., Kalgin, I., Yanchenko, A., Ivanov, P., Goncharenko, A.: onnx2torch (2021). https:\/\/enot.ai\/. version: x.y.z"},{"key":"15_CR10","doi-asserted-by":"crossref","unstructured":"Gilchrist, W.: Statistical modelling with quantile functions (2000)","DOI":"10.1201\/9781420035919"},{"key":"15_CR11","unstructured":"Han, J., Kamber, M., Pei, J.: Data Mining Concepts and Techniques, 3rd edn. (2012)"},{"key":"15_CR12","doi-asserted-by":"publisher","unstructured":"Huang, Z., Sen, R., Liu, J., Wu, E.: Joinboost: Grow trees over normalized data using only SQL. Proc. VLDB Endow. 16(11), 3071\u20133084 (2023). https:\/\/doi.org\/10.14778\/3611479.3611509","DOI":"10.14778\/3611479.3611509"},{"key":"15_CR13","doi-asserted-by":"crossref","unstructured":"Kumar, A., Naughton, J., Patel, J.M.: Learning generalized linear models over normalized data. In: Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data, pp. 1969\u20131984 (2015)","DOI":"10.1145\/2723372.2723713"},{"key":"15_CR14","unstructured":"Levy, A.Y., Mumick, I.S., Sagiv, Y.: Query optimization by predicate move-around. In: VLDB, vol.\u00a094, pp. 12\u201315 (1994)"},{"key":"15_CR15","doi-asserted-by":"crossref","unstructured":"Li, S., Chen, L., Kumar, A.: Enabling and optimizing non-linear feature interactions in factorized linear algebra. In: Proceedings of the 2019 International Conference on Management of Data, pp. 1571\u20131588 (2019)","DOI":"10.1145\/3299869.3319878"},{"key":"15_CR16","doi-asserted-by":"crossref","unstructured":"Lucchese, C., Nardini, F.M., Orlando, S., Perego, R., Tonellotto, N., Venturini, R.: Quickscorer: a fast algorithm to rank documents with additive ensembles of regression trees. In: SIGIR \u201915 , pp. 73\u201382 (2015)","DOI":"10.1145\/2766462.2767733"},{"key":"15_CR17","doi-asserted-by":"crossref","unstructured":"Mangal, A., Kumar, N.: Using big data to enhance the Bosch production line performance: a Kaggle challenge. In: 2016 IEEE International Conference on Big Data (Big Data), pp. 2029\u20132035. IEEE (2016)","DOI":"10.1109\/BigData.2016.7840826"},{"issue":"2","key":"15_CR18","doi-asserted-by":"publisher","first-page":"230","DOI":"10.14778\/3149193.3149202","volume":"11","author":"G Psaropoulos","year":"2017","unstructured":"Psaropoulos, G., Legler, T., May, N., Ailamaki, A.: Interleaving with coroutines: a practical approach for robust index joins. Proc. VLDB Endowment 11(2), 230\u2013242 (2017)","journal-title":"Proc. VLDB Endowment"},{"key":"15_CR19","doi-asserted-by":"crossref","unstructured":"Raasveldt, M., Muehleisen, H., et\u00a0al.: DuckDB. In: Proceedings of the 2019 International Conference on Management of Data. ACM (2019)","DOI":"10.1145\/3299869.3320212"},{"key":"15_CR20","unstructured":"Roh, H.: Understanding fat-tailed distribution (2020). https:\/\/towardsdatascience.com\/journey-to-tempered-stable-distribution-part-1-fat-tailed-distribution-958d28bc20c"},{"key":"15_CR21","doi-asserted-by":"publisher","unstructured":"Schleich, M., Olteanu, D., Abo\u00a0Khamis, M., Ngo, H.Q., Nguyen, X.: A layered aggregate engine for analytics workloads. In: Proceedings of the 2019 International Conference on Management of Data. SIGMOD \u201919, New York, NY, USA, pp. 1642\u20131659. Association for Computing Machinery (2019).https:\/\/doi.org\/10.1145\/3299869.3324961","DOI":"10.1145\/3299869.3324961"},{"key":"15_CR22","doi-asserted-by":"publisher","unstructured":"Schleich, M., Olteanu, D., Ciucanu, R.: Learning linear regression models over factorized joins. In: Proceedings of the 2016 International Conference on Management of Data. SIGMOD \u201916, New York, NY, USA, p. 3\u201318. Association for Computing Machinery (2016https:\/\/doi.org\/10.1145\/2882903.2882939","DOI":"10.1145\/2882903.2882939"},{"key":"15_CR23","doi-asserted-by":"crossref","unstructured":"Siegel, A.F.: Chapter 7 - random variables: working with uncertain numbers. In: Siegel, A.F. (ed.) Practical Business Statistics (Sixth Edition), 6th edn., pp. 155\u2013186. Academic Press (2012)","DOI":"10.1016\/B978-0-12-385208-3.00007-9"},{"key":"15_CR24","unstructured":"Sonnenburg, S., Franc, V., Yom-Tov, E., Sebag, M.: Pascal large scale learning challenge. In: 25th International Conference on Machine Learning (ICML2008) Workshop, vol.\u00a010, pp. 1937\u20131953 (2008)"},{"issue":"11","key":"15_CR25","doi-asserted-by":"publisher","first-page":"2994","DOI":"10.14778\/3551793.3551847","volume":"15","author":"X Wang","year":"2022","unstructured":"Wang, X., et al.: Connectorx: accelerating data loading from databases to dataframes. Proc. VLDB Endowment 15(11), 2994\u20133003 (2022)","journal-title":"Proc. VLDB Endowment"},{"key":"15_CR26","doi-asserted-by":"crossref","unstructured":"Yan, C., He, Y.: Auto-suggest: learning-to-recommend data preparation steps using data science notebooks. In: Proceedings of the 2020 ACM SIGMOD International Conference on Management of Data. SIGMOD \u201920, pp. 1539\u20131554 (2020)","DOI":"10.1145\/3318464.3389738"},{"key":"15_CR27","unstructured":"Zheng, A., Casari, A.: Feature Engineering for Machine Learning: Principles and Techniques for Data Scientists, 1st edn. O\u2019Reilly Media, Inc. (2018)"}],"container-title":["Lecture Notes in Computer Science","Database Systems for Advanced Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-3827-0_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T13:03:53Z","timestamp":1781874233000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-3827-0_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819538263","9789819538270"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-3827-0_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"20 June 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DASFAA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Database Systems for Advanced Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Singapore","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Singapore","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 May 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 May 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"dasfaa2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/dasfaa2025.github.io","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}