{"id":"https://openalex.org/W4381329183","doi":"https://doi.org/10.1145/3589279","title":"QaaD (Query-as-a-Data): Scalable Execution of Massive Number of Small Queries in Spark","display_name":"QaaD (Query-as-a-Data): Scalable Execution of Massive Number of Small Queries in Spark","publication_year":2023,"publication_date":"2023-06-13","ids":{"openalex":"https://openalex.org/W4381329183","doi":"https://doi.org/10.1145/3589279"},"language":"en","primary_location":{"id":"doi:10.1145/3589279","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3589279","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","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/A5029796268","display_name":"Yeonsu Park","orcid":"https://orcid.org/0009-0001-9355-2140"},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Yeonsu Park","raw_affiliation_strings":["POSTECH, Pohang, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"POSTECH, Pohang, Republic of Korea","institution_ids":["https://openalex.org/I123900574"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010776108","display_name":"Byungchul Tak","orcid":"https://orcid.org/0000-0002-8204-6816"},"institutions":[{"id":"https://openalex.org/I31419693","display_name":"Kyungpook National University","ror":"https://ror.org/040c17130","country_code":"KR","type":"education","lineage":["https://openalex.org/I31419693"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Byungchul Tak","raw_affiliation_strings":["Kyungpook National University, Daegu, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Kyungpook National University, Daegu, Republic of Korea","institution_ids":["https://openalex.org/I31419693"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035744252","display_name":"Wook-Shin Han","orcid":"https://orcid.org/0000-0001-9206-9563"},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Wook-Shin Han","raw_affiliation_strings":["POSTECH, Pohang, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"POSTECH, Pohang, Republic of Korea","institution_ids":["https://openalex.org/I123900574"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5029796268"],"corresponding_institution_ids":["https://openalex.org/I123900574"],"apc_list":null,"apc_paid":null,"fwci":0.9178,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.78482763,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"1","issue":"2","first_page":"1","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.998199999332428,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.995199978351593,"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":0.8625607490539551},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.7996422052383423},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6591759324073792},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.5773212909698486},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.570160984992981},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5128465294837952},{"id":"https://openalex.org/keywords/small-data","display_name":"Small data","score":0.47877776622772217},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.45809823274612427},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.42599090933799744},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.42155390977859497},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.4204632043838501},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3711172640323639},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.36157211661338806},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.35328829288482666},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.27567005157470703},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1585749089717865},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09182903170585632},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.08741205930709839}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8625607490539551},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.7996422052383423},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6591759324073792},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5773212909698486},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.570160984992981},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5128465294837952},{"id":"https://openalex.org/C2779280203","wikidata":"https://www.wikidata.org/wiki/Q17121211","display_name":"Small data","level":2,"score":0.47877776622772217},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.45809823274612427},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.42599090933799744},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.42155390977859497},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.4204632043838501},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3711172640323639},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.36157211661338806},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.35328829288482666},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27567005157470703},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1585749089717865},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09182903170585632},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.08741205930709839},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3589279","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3589279","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.4300000071525574,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1861377444","https://openalex.org/W2092086632","https://openalex.org/W2098935637","https://openalex.org/W2104993419","https://openalex.org/W2565167788","https://openalex.org/W2724504565","https://openalex.org/W2762847354","https://openalex.org/W2763382507","https://openalex.org/W2782674619","https://openalex.org/W2797577490","https://openalex.org/W2799237774","https://openalex.org/W2808182399","https://openalex.org/W2889140904","https://openalex.org/W2912516925","https://openalex.org/W2925032266","https://openalex.org/W2951887793","https://openalex.org/W2967032974","https://openalex.org/W2983968971","https://openalex.org/W3009373060","https://openalex.org/W3138831836","https://openalex.org/W3163876710","https://openalex.org/W3164472442","https://openalex.org/W3197336984","https://openalex.org/W3198638494","https://openalex.org/W4281785343","https://openalex.org/W4282583266"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2027972911","https://openalex.org/W2146343568","https://openalex.org/W2013643406","https://openalex.org/W2157978810","https://openalex.org/W2597809628","https://openalex.org/W3046370962"],"abstract_inverted_index":{"Spark":[0,32,83,194],"big":[1],"data":[2,30,173,180],"processing":[3,47],"platform":[4],"is":[5,33,85,184],"heavily":[6],"used":[7],"in":[8,78],"today's":[9],"IT":[10],"services":[11],"for":[12,21,139,196],"various":[13,48,73],"critical":[14],"applications":[15],"such":[16],"as":[17,162],"machine":[18],"learning":[19],"tasks":[20],"service":[22],"recommendations":[23],"or":[24],"massive":[25],"volumes":[26],"of":[27,44,66,91,95,122,125,155,160,164,170],"raw":[28],"sales":[29],"analysis.":[31],"designed":[34],"to":[35,87,100,151,186,189],"deliver":[36,187],"high":[37,42],"performance":[38],"by":[39,117],"enabling":[40],"a":[41,92,108,147],"degree":[43],"parallelism":[45],"while":[46],"heavy-weight":[49],"queries":[50,70,97,127,132,161],"that":[51,63,112,182],"require":[52],"homogeneous":[53],"operations":[54],"on":[55],"large":[56,93,131],"data.":[57],"However,":[58],"it":[59],"has":[60],"been":[61],"observed":[62],"workloads":[64,89,123],"made":[65,90,124],"small":[67,96,104,126,197],"and":[68,133,166],"short-running":[69],"coming":[71],"from":[72],"sources":[74],"are":[75],"becoming":[76],"dominant":[77],"practice.":[79],"Unfortunately,":[80],"the":[81,158],"current":[82],"architecture":[84],"unfit":[86],"process":[88],"number":[94],"optimally":[98],"due":[99],"excessive":[101],"I/Os":[102],"with":[103,130],"computations.":[105],"We":[106],"present":[107],"technique,":[109],"called":[110],"QaaD,":[111],"addresses":[113],"this":[114],"problem":[115],"fundamentally":[116],"applying":[118],"i)":[119],"transparent":[120],"conversion":[121],"into":[128],"one":[129],"ii)":[134],"dynamic":[135],"partition":[136],"size":[137],"adjustment":[138],"runtime":[140],"overhead":[141],"minimization.":[142],"For":[143],"this,":[144],"we":[145],"introduce":[146],"new":[148],"abstraction,":[149],"microRDD,":[150],"support":[152],"our":[153],"design":[154],"query":[156,198],"merging,":[157],"embedding":[159],"part":[163],"data,":[165],"an":[167],"opportunistic":[168],"sharing":[169],"common":[171],"input":[172],"among":[174],"queries.":[175],"Comprehensive":[176],"evaluation":[177],"using":[178],"real-world":[179],"shows":[181],"QaaD":[183],"able":[185],"10.6x":[188],"36.6x":[190],"speed-up":[191],"against":[192],"standard":[193],"executions":[195],"workloads.":[199]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}