{"id":"https://openalex.org/W4213436600","doi":"https://doi.org/10.1109/tkde.2022.3153651","title":"A Scalable Query-Aware Enormous Database Generator for Database Evaluation","display_name":"A Scalable Query-Aware Enormous Database Generator for Database Evaluation","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4213436600","doi":"https://doi.org/10.1109/tkde.2022.3153651"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2022.3153651","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2022.3153651","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066085693","display_name":"Qingshuai Wang","orcid":"https://orcid.org/0000-0001-9420-5899"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingshuai Wang","raw_affiliation_strings":["School of Data Science and Engineering, East China Normal University, 12655 Shanghai, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Data Science and Engineering, East China Normal University, 12655 Shanghai, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100779256","display_name":"Yuming Li","orcid":"https://orcid.org/0000-0002-6489-3106"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuming Li","raw_affiliation_strings":["Database Group, Huawei, Shanghai, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Database Group, Huawei, Shanghai, Shanghai, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101550330","display_name":"Rong Zhang","orcid":"https://orcid.org/0009-0000-1101-7316"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rong Zhang","raw_affiliation_strings":["School of Data Science and Engineering, East China Normal University, 12655 Shanghai, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Data Science and Engineering, East China Normal University, 12655 Shanghai, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052821868","display_name":"Ke Shu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ke Shu","raw_affiliation_strings":["Testing Group, PingCAP, Beijing, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Testing Group, PingCAP, Beijing, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100633297","display_name":"Zhenjie Zhang","orcid":"https://orcid.org/0009-0000-9080-7489"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhenjie Zhang","raw_affiliation_strings":["Data Science, Neuron Mobility Pte. Ltd., Singapore, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data Science, Neuron Mobility Pte. Ltd., Singapore, Singapore, Singapore","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101511862","display_name":"Aoying Zhou","orcid":"https://orcid.org/0000-0002-4665-7302"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Aoying Zhou","raw_affiliation_strings":["School of Data Science and Engineering, East China Normal University, 12655 Shanghai, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Data Science and Engineering, East China Normal University, 12655 Shanghai, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7923,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.70453802,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9962000250816345,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.906511664390564},{"id":"https://openalex.org/keywords/query-optimization","display_name":"Query optimization","score":0.6598466634750366},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.6139124035835266},{"id":"https://openalex.org/keywords/view","display_name":"View","score":0.5825102925300598},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5229949951171875},{"id":"https://openalex.org/keywords/database-tuning","display_name":"Database tuning","score":0.4977264702320099},{"id":"https://openalex.org/keywords/database-testing","display_name":"Database testing","score":0.440623939037323},{"id":"https://openalex.org/keywords/joins","display_name":"Joins","score":0.4326532185077667},{"id":"https://openalex.org/keywords/parallel-database","display_name":"Parallel database","score":0.4313860535621643},{"id":"https://openalex.org/keywords/online-aggregation","display_name":"Online aggregation","score":0.41574549674987793},{"id":"https://openalex.org/keywords/database-design","display_name":"Database design","score":0.4077679216861725},{"id":"https://openalex.org/keywords/sargable","display_name":"Sargable","score":0.4014570415019989},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.27682721614837646},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.20303389430046082},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.11237549781799316},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10956788063049316}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.906511664390564},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.6598466634750366},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.6139124035835266},{"id":"https://openalex.org/C54239708","wikidata":"https://www.wikidata.org/wiki/Q1329910","display_name":"View","level":3,"score":0.5825102925300598},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5229949951171875},{"id":"https://openalex.org/C107535962","wikidata":"https://www.wikidata.org/wiki/Q2459880","display_name":"Database tuning","level":4,"score":0.4977264702320099},{"id":"https://openalex.org/C78161392","wikidata":"https://www.wikidata.org/wiki/Q5227414","display_name":"Database testing","level":4,"score":0.440623939037323},{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.4326532185077667},{"id":"https://openalex.org/C2777541480","wikidata":"https://www.wikidata.org/wiki/Q2051600","display_name":"Parallel database","level":2,"score":0.4313860535621643},{"id":"https://openalex.org/C24028149","wikidata":"https://www.wikidata.org/wiki/Q7094056","display_name":"Online aggregation","level":5,"score":0.41574549674987793},{"id":"https://openalex.org/C148840519","wikidata":"https://www.wikidata.org/wiki/Q1049878","display_name":"Database design","level":2,"score":0.4077679216861725},{"id":"https://openalex.org/C192939062","wikidata":"https://www.wikidata.org/wiki/Q104840822","display_name":"Sargable","level":4,"score":0.4014570415019989},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.27682721614837646},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.20303389430046082},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.11237549781799316},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10956788063049316}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tkde.2022.3153651","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2022.3153651","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5060083305","display_name":null,"funder_award_id":"No. 62072179","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1578512165","https://openalex.org/W1965085982","https://openalex.org/W1967927843","https://openalex.org/W1971885140","https://openalex.org/W1992730709","https://openalex.org/W1995446447","https://openalex.org/W2003638749","https://openalex.org/W2008451927","https://openalex.org/W2022431239","https://openalex.org/W2057516979","https://openalex.org/W2072737285","https://openalex.org/W2082323325","https://openalex.org/W2113531724","https://openalex.org/W2121084172","https://openalex.org/W2144319429","https://openalex.org/W2151583733","https://openalex.org/W2159114365","https://openalex.org/W2171831739","https://openalex.org/W2345040254","https://openalex.org/W2548762611","https://openalex.org/W2588045990","https://openalex.org/W3086150815","https://openalex.org/W4239146630","https://openalex.org/W6676078874","https://openalex.org/W6749997383","https://openalex.org/W6753333625"],"related_works":["https://openalex.org/W2521597029","https://openalex.org/W2129469317","https://openalex.org/W2041090168","https://openalex.org/W2365999782","https://openalex.org/W2090529051","https://openalex.org/W2368118519","https://openalex.org/W4252101311","https://openalex.org/W2545191987","https://openalex.org/W2022431239","https://openalex.org/W4247180345"],"abstract_inverted_index":{"Query-aware":[0],"synthetic":[1],"data":[2,28,49,60,78,94,105,126],"generation":[3,29,61,95],"is":[4],"an":[5],"essential":[6],"and":[7,21,38,63,74,91,109],"highly":[8],"challenging":[9],"task,":[10],"important":[11],"for":[12,124],"database":[13,18],"management":[14],"system":[15],"(DBMS)":[16],"testing,":[17],"application":[19],"testing":[20],"application-driven":[22],"benchmarking.":[23],"Prior":[24],"studies":[25],"on":[26,139],"query-aware":[27,69],"suffer":[30],"common":[31],"problems":[32],"of":[33,67,117],"limited":[34],"parallelization,":[35],"poor":[36],"scalability,":[37],"excessive":[39],"memory":[40,111],"consumption,":[41],"making":[42],"these":[43],"systems":[44],"unsatisfactory":[45],"to":[46,53,101],"terabyte":[47],"scale":[48],"generation.":[50,127],"In":[51],"order":[52],"fill":[54],"the":[55,58,64,84,92,98,136],"gap":[56],"between":[57],"existing":[59],"techniques":[62],"emerging":[65],"demands":[66],"enormous":[68],"test":[70,99],"databases,":[71],"we":[72],"design":[73],"implement":[75],"a":[76,143],"new":[77,93],"generator,":[79],"called":[80],"Touchstone.":[81],"Touchstone":[82,133],"adopts":[83],"random":[85],"sampling":[86],"algorithm":[87],"instantiating":[88],"query":[89],"parameters":[90],"schema":[96],"generating":[97],"database,":[100],"achieve":[102],"fully":[103],"parallel":[104],"generation,":[106],"linear":[107],"scalability":[108],"austere":[110],"consumption.":[112],"It":[113],"has":[114],"full":[115],"support":[116],"outer":[118],"joins":[119],"as":[120,122],"well":[121],"non-equi-joins":[123],"application-oriented":[125],"Our":[128],"experimental":[129],"results":[130],"show":[131],"that":[132],"consistently":[134],"outperforms":[135],"state-of-the-art":[137],"solution":[138],"TPC-H":[140],"workload":[141],"by":[142],"1000":[144],"speedup":[145],"without":[146],"sacrificing":[147],"simulation":[148],"fidelity.":[149]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-17T09:13:05.818461","created_date":"2025-10-10T00:00:00"}