{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T17:40:32Z","timestamp":1778002832026,"version":"3.51.4"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2025,1,22]],"date-time":"2025-01-22T00:00:00Z","timestamp":1737504000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,22]],"date-time":"2025-01-22T00:00:00Z","timestamp":1737504000000},"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":["Front. Comput. Sci."],"published-print":{"date-parts":[[2025,9]]},"DOI":"10.1007\/s11704-024-40509-4","type":"journal-article","created":{"date-parts":[[2025,1,22]],"date-time":"2025-01-22T15:33:31Z","timestamp":1737560011000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["LRP: learned robust data partitioning for efficient processing of large dynamic queries"],"prefix":"10.1007","volume":"19","author":[{"given":"Pengju","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pan","family":"Cai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kai","family":"Zhong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cuiping","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,1,22]]},"reference":[{"issue":"1","key":"40509_CR1","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1145\/3148.3161","volume":"10","author":"R W Taylor","year":"1985","unstructured":"Taylor R W, Sacca D, Wiederhold G. Database partitioning in a cluster of processors. ACM Transactions on Database Systems (TODS), 1985, 10(1): 29\u201356","journal-title":"ACM Transactions on Database Systems (TODS)"},{"key":"40509_CR2","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1145\/50202.50213","volume-title":"Proceedings of 1988 ACM SIGMOD International Conference on Management of Data","author":"G Copeland","year":"1988","unstructured":"Copeland G, Alexander W, Boughter E, Keller T. Data placement in bubba. In: Proceedings of 1988 ACM SIGMOD International Conference on Management of Data. 1988, 99\u2013108"},{"key":"40509_CR3","first-page":"273","volume-title":"Proceedings of the 26th International Conference on Very Large Data Bases","author":"T St\u00f6hr","year":"2000","unstructured":"St\u00f6hr T, M\u00e4rtens H, Rahm E. Multi-dimensional database allocation for parallel data warehouses. In: Proceedings of the 26th International Conference on Very Large Data Bases. 2000, 273\u2013284"},{"issue":"9","key":"40509_CR4","doi-asserted-by":"publisher","first-page":"509","DOI":"10.1145\/361002.361007","volume":"18","author":"J L Bentley","year":"1975","unstructured":"Bentley J L. Multidimensional binary search trees used for associative searching. Communications of the ACM, 1975, 18(9): 509\u2013517","journal-title":"Communications of the ACM"},{"issue":"12","key":"40509_CR5","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, Chai C. AnalyticDB: real-time OLAP database system at alibaba cloud. Proceedings of the VLDB Endowment, 2019, 12(12): 2059\u20132070","journal-title":"Proceedings of the VLDB Endowment"},{"key":"40509_CR6","first-page":"383","volume-title":"Proceedings of the 16th International Conference on Scientific and Statistical Database Management","author":"S Papadomanolakis","year":"2004","unstructured":"Papadomanolakis S, Ailamaki A. AutoPart: automating schema design for large scientific databases using data partitioning. In: Proceedings of the 16th International Conference on Scientific and Statistical Database Management. 2004, 383\u2013392"},{"key":"40509_CR7","doi-asserted-by":"publisher","first-page":"1115","DOI":"10.1145\/2588555.2610515","volume-title":"Proceedings of 2014 ACM SIGMOD International Conference on Management of Data","author":"L Sun","year":"2014","unstructured":"Sun L, Franklin M J, Krishnan S, Xin R S. Fine-grained partitioning for aggressive data skipping. In: Proceedings of 2014 ACM SIGMOD International Conference on Management of Data. 2014, 1115\u20131126"},{"key":"40509_CR8","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1145\/3318464.3389770","volume-title":"Proceedings of 2020 ACM SIGMOD International Conference on Management of Data","author":"Z Ang","year":"2020","unstructured":"Ang Z, Chandramouli B, Wang C, Gehrke J, Li Y, Minhas U F, Larson P\u00c5, Kossmann D, Acharya R. Qd-tree: learning data layouts for big data analytics. In: Proceedings of 2020 ACM SIGMOD International Conference on Management of Data. 2020, 193\u2013208"},{"key":"40509_CR9","first-page":"123","volume-title":"Proceedings of the 38th IEEE International Conference on Data Engineering","author":"Z Li","year":"2022","unstructured":"Li Z, Yiu M L, Chan T N. PAW: data partitioning meets workload variance. In: Proceedings of the 38th IEEE International Conference on Data Engineering. 2022, 123\u2013135"},{"issue":"4","key":"40509_CR10","doi-asserted-by":"publisher","first-page":"421","DOI":"10.14778\/3025111.3025123","volume":"10","author":"L Sun","year":"2016","unstructured":"Sun L, Franklin M J, Wang J, Wu E. Skipping-oriented partitioning for columnar layouts. Proceedings of the VLDB Endowment, 2016, 10(4): 421\u2013432","journal-title":"Proceedings of the VLDB Endowment"},{"issue":"13","key":"40509_CR11","doi-asserted-by":"publisher","first-page":"2062","DOI":"10.14778\/2831360.2831361","volume":"8","author":"C Li","year":"2015","unstructured":"Li C, Markl V, Aly A M, Mahmood A R, Hassan M S, Aref W G, Ouzzani M, Elmeleegy H, Qadah T. AQWA: adaptive query workload aware partitioning of big spatial data. Proceedings of the VLDB Endowment, 2015, 8(13): 2062\u20132073","journal-title":"Proceedings of the VLDB Endowment"},{"key":"40509_CR12","first-page":"397","volume-title":"Proceedings of the 9th ACM International Conference on Web Search and Data Mining","author":"A M Aly","year":"2016","unstructured":"Aly A M, Elmeleegy H, Qi Y, Aref W. Kangaroo: workload-aware processing of range data and range queries in hadoop. In: Proceedings of the 9th ACM International Conference on Web Search and Data Mining. 2016, 397\u2013406"},{"issue":"5","key":"40509_CR13","doi-asserted-by":"publisher","first-page":"589","DOI":"10.14778\/3055540.3055551","volume":"10","author":"Y Lu","year":"2017","unstructured":"Lu Y, Shanbhag A, Jindal A, Madden S. AdaptDB: adaptive partitioning for distributed joins. Proceedings of the VLDB Endowment, 2017, 10(5): 589\u2013600","journal-title":"Proceedings of the VLDB Endowment"},{"key":"40509_CR14","doi-asserted-by":"publisher","first-page":"418","DOI":"10.1145\/3448016.3457270","volume-title":"Proceedings of 2021 International Conference on Management of Data","author":"J Ding","year":"2021","unstructured":"Ding J, Minhas U F, Chandramouli B, Wang C, Li Y, Li Y, Kossmann D, Gehrke J, Kraska T. Instance-optimized data layouts for cloud analytics workloads. In: Proceedings of 2021 International Conference on Management of Data. 2021, 418\u2013431"},{"key":"40509_CR15","unstructured":"TPC-H benchmark. See tpc.org\/tpch\/ website, 1999."},{"issue":"4","key":"40509_CR16","doi-asserted-by":"publisher","first-page":"705","DOI":"10.2307\/1419730","volume":"76","author":"F Rosenblatt","year":"1963","unstructured":"Rosenblatt F. Principles of neurodynamics: perceptrons and the theory of brain mechanisms. The American Journal of Psychology, 1963, 76(4): 705\u2013707","journal-title":"The American Journal of Psychology"},{"issue":"8","key":"40509_CR17","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter S, Schmidhuber J. Long short-term memory. Neural Computation, 1997, 9(8): 1735\u20131780","journal-title":"Neural Computation"},{"key":"40509_CR18","first-page":"1","volume-title":"Proceedings of the 26th IEEE Symposium on Mass Storage Systems and Technologies (MSST)","author":"K Shvachko","year":"2010","unstructured":"Shvachko K, Kuang H, Radia S, Chansler R. The hadoop distributed file system. In: Proceedings of the 26th IEEE Symposium on Mass Storage Systems and Technologies (MSST). 2010, 1\u201310"},{"key":"40509_CR19","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1145\/3127479.3131613","volume-title":"Proceedings of 2017 Symposium on Cloud Computing","author":"A Shanbhag","year":"2017","unstructured":"Shanbhag A, Jindal A, Madden S, Quiane J, Elmore A J. A robust partitioning scheme for ad-hoc query workloads. In: Proceedings of 2017 Symposium on Cloud Computing. 2017, 229\u2013241"},{"issue":"12","key":"40509_CR20","doi-asserted-by":"publisher","first-page":"3072","DOI":"10.14778\/3415478.3415535","volume":"13","author":"D Huang","year":"2020","unstructured":"Huang D, Liu Q, Cui Q, Fang Z, Ma X, Xu F, Shen L, Tang L, Zhou Y, Huang M, Wei W, Liu C, Zhang J, Li J, Wu X, Song L, Sun R, Yu S, Zhao L, Cameron N, Pei L, Tang X. TIDB: a raft-based HTAP database. Proceedings of the VLDB Endowment, 2020, 13(12): 3072\u20133084","journal-title":"Proceedings of the VLDB Endowment"},{"key":"40509_CR21","unstructured":"ClickHouse: an open-source columnar database management system. See clickhouse.com\/docs\/en\/observability\/managing-data website, 2016"},{"key":"40509_CR22","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1145\/2882903.2903741","volume-title":"Proceedings of 2016 International Conference on Management of Data","author":"B Dageville","year":"2016","unstructured":"Dageville B, Cruanes T, Zukowski M, Antonov V, Avanes A, Bock J, Claybaugh J, Engovatov D, Hentschel M, Huang J S, Lee A W, Motivala A, Munir A Q, Pelley S, Povinec P, Rahn G, Triantafyllis S, Unterbrunner P. The snowflake elastic data warehouse. In: Proceedings of 2016 International Conference on Management of Data. 2016, 215\u2013226"},{"key":"40509_CR23","first-page":"476","volume-title":"Proceedings of the 24th International Conference on Very Large Data Bases","author":"G Moerkotte","year":"1998","unstructured":"Moerkotte G. Small materialized aggregates: a light weight index structure for data warehousing. In: Proceedings of the 24th International Conference on Very Large Data Bases. 1998, 476\u2013487"},{"key":"40509_CR24","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1007\/978-3-642-03730-6_10","volume-title":"Proceedings of the 11th International Conference on Data Warehousing and Knowledge Discovery","author":"G Graefe","year":"2009","unstructured":"Graefe G. Fast loads and fast queries. In: Proceedings of the 11th International Conference on Data Warehousing and Knowledge Discovery. 2009, 111\u2013124"},{"key":"40509_CR25","doi-asserted-by":"publisher","first-page":"898","DOI":"10.1145\/3448016.3457547","volume-title":"Proceedings of 2021 International Conference on Management of Data","author":"D Kang","year":"2021","unstructured":"Kang D, Jiang R, Blanas S. Jigsaw: a data storage and query processing engine for irregular table partitioning. In: Proceedings of 2021 International Conference on Management of Data. 2021, 898\u2013911"},{"key":"40509_CR26","first-page":"1287","volume-title":"Proceedings of 2012 IEEE Network Operations and Management Symposium","author":"A Han","year":"2012","unstructured":"Han A, Yan X, Tao S, Anerousis N. Workload characterization and pre diction in the cloud: a multiple time series approach. In: Proceedings of 2012 IEEE Network Operations and Management Symposium. 2012, 1287\u20131294"},{"key":"40509_CR27","first-page":"1","volume-title":"Proceedings of the 8th Biennial Conference on Innovative Data Systems Research","author":"A Pavlo","year":"2017","unstructured":"Pavlo A, Angulo G, Arulraj J, Lin H, Lin J, Ma L, Menon P, Mowry T C, Perron M, Quah I, Santurkar S, Tomasic A, Toor S, Van Aken D, Wang Z, Wu Y, Xian R, Zhang T. Self-driving database management systems. In: Proceedings of the 8th Biennial Conference on Innovative Data Systems Research. 2017, 1"},{"key":"40509_CR28","doi-asserted-by":"publisher","first-page":"631","DOI":"10.1145\/3183713.3196908","volume-title":"Proceedings of 2018 International Conference on Management of Data","author":"L Ma","year":"2018","unstructured":"Ma L, Van Aken D, Hefny A, Mezerhane G, Pavlo A, Gordon G J. Query-based workload forecasting for self-driving database management systems. In: Proceedings of 2018 International Conference on Management of Data. 2018, 631\u2013645"},{"key":"40509_CR29","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1145\/3318464.3389704","volume-title":"Proceedings of 2020 ACM SIGMOD International Conference on Management of Data","author":"B Hilprecht","year":"2020","unstructured":"Hilprecht B, Binnig C, R\u00f6hm U. Learning a partitioning advisor for cloud databases. In: Proceedings of 2020 ACM SIGMOD International Conference on Management of Data. 2020, 143\u2013157"},{"issue":"1","key":"40509_CR30","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1145\/3588948","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, 2023, 1(1): 94","journal-title":"Proceedings of the ACM on Management of Data"},{"key":"40509_CR31","first-page":"65","volume-title":"Proceedings of the 5th International Workshop on Business Intelligence for the Real-Time Enterprise","author":"A Jindal","year":"2011","unstructured":"Jindal A, Dittrich J. Relax and let the database do the partitioning online. In: Proceedings of the 5th International Workshop on Business Intelligence for the Real-Time Enterprise. 2011, 65\u201380"},{"issue":"1","key":"40509_CR32","doi-asserted-by":"publisher","first-page":"72","DOI":"10.14778\/3485450.3485458","volume":"15","author":"J Wang","year":"2021","unstructured":"Wang J, Chai C, Liu J, Li G. Face: a normalizing flow based cardinality estimator. Proceedings of the VLDB Endowment, 2021, 15(1): 72\u201384","journal-title":"Proceedings of the VLDB Endowment"},{"issue":"1","key":"40509_CR33","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1080\/00401706.1970.10488634","volume":"12","author":"A E Hoerl","year":"1970","unstructured":"Hoerl A E, Kennard R W. Ridge regression: biased estimation for nonorthogonal problems. Technometrics, 1970, 12(1): 55\u201367","journal-title":"Technometrics"},{"issue":"1\u20132","key":"40509_CR34","first-page":"330","volume":"3","author":"E Bertino","year":"2010","unstructured":"Bertino E, Atzeni P, Tan K L, Chen Y, Tay Y C, Melnik S, Gubarev A, Long J J, Romer G, Shivakumar S, Tolton M, Vassilakis T. Dremel: interactive analysis of web-scale datasets. Proceedings of the VLDB Endowment, 2010, 3(1\u20132): 330\u2013339","journal-title":"Proceedings of the VLDB Endowment"},{"key":"40509_CR35","unstructured":"Ray: an open source framework to build and scale your ML and Python applications. See docs.ray.io\/en\/latest\/ website, 2017"},{"key":"40509_CR36","unstructured":"TPC-DS benchmark. See www.tpc.org\/tpcds\/ website, 2005"},{"key":"40509_CR37","unstructured":"JOB benchmark. See developer.imdb.com\/non-commercial-datasets\/ website, 2016"},{"key":"40509_CR38","unstructured":"ClickBench benchmark. See github.com\/ClickHouse\/ClickBench website, 2019"}],"container-title":["Frontiers of Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11704-024-40509-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11704-024-40509-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11704-024-40509-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,22]],"date-time":"2025-01-22T15:33:39Z","timestamp":1737560019000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11704-024-40509-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,22]]},"references-count":38,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2025,9]]}},"alternative-id":["40509"],"URL":"https:\/\/doi.org\/10.1007\/s11704-024-40509-4","relation":{},"ISSN":["2095-2228","2095-2236"],"issn-type":[{"value":"2095-2228","type":"print"},{"value":"2095-2236","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,22]]},"assertion":[{"value":"21 May 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 September 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 January 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Competing interests The authors declare that they have no competing interests or financial conflicts to disclose.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics"}}],"article-number":"199607"}}