{"id":"https://openalex.org/W4389072944","doi":"https://doi.org/10.48550/arxiv.2311.14311","title":"RelJoin: Relative-cost-based Selection of Distributed Join Methods for Query Plan Optimization","display_name":"RelJoin: Relative-cost-based Selection of Distributed Join Methods for Query Plan Optimization","publication_year":2023,"publication_date":"2023-11-24","ids":{"openalex":"https://openalex.org/W4389072944","doi":"https://doi.org/10.48550/arxiv.2311.14311"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2311.14311","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2311.14311","pdf_url":"https://arxiv.org/pdf/2311.14311","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2311.14311","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067631851","display_name":"Feng Liang","orcid":"https://orcid.org/0000-0002-9393-6224"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang, F.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079339840","display_name":"Francis C. M. Lau","orcid":"https://orcid.org/0000-0002-8279-0899"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lau, F. C. M.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008897366","display_name":"Hao Cui","orcid":"https://orcid.org/0000-0002-7574-2004"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cui, H.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017943466","display_name":"Yuan-Fang Li","orcid":"https://orcid.org/0000-0003-4651-2821"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Y.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083464792","display_name":"Binshan Lin","orcid":"https://orcid.org/0000-0002-8481-302X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, B.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100424922","display_name":"Chong Li","orcid":"https://orcid.org/0000-0001-8957-7110"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, C.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101646860","display_name":"Xin Hu","orcid":"https://orcid.org/0000-0002-8915-3526"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, X.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9994999766349792,"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":0.9994999766349792,"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/T11106","display_name":"Data Management and Algorithms","score":0.9957000017166138,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9944999814033508,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8658697009086609},{"id":"https://openalex.org/keywords/joins","display_name":"Joins","score":0.7980591058731079},{"id":"https://openalex.org/keywords/query-optimization","display_name":"Query optimization","score":0.6592515707015991},{"id":"https://openalex.org/keywords/join","display_name":"Join (topology)","score":0.626360297203064},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6156458258628845},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6144620180130005},{"id":"https://openalex.org/keywords/query-plan","display_name":"Query plan","score":0.5744737982749939},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5691897869110107},{"id":"https://openalex.org/keywords/distributed-database","display_name":"Distributed database","score":0.48667246103286743},{"id":"https://openalex.org/keywords/cardinality","display_name":"Cardinality (data modeling)","score":0.48538100719451904},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.38404661417007446},{"id":"https://openalex.org/keywords/sargable","display_name":"Sargable","score":0.3171064853668213},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.303754985332489},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.16998541355133057},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.16193222999572754},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.09516113996505737}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8658697009086609},{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.7980591058731079},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.6592515707015991},{"id":"https://openalex.org/C2776124973","wikidata":"https://www.wikidata.org/wiki/Q3183033","display_name":"Join (topology)","level":2,"score":0.626360297203064},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6156458258628845},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6144620180130005},{"id":"https://openalex.org/C2779729312","wikidata":"https://www.wikidata.org/wiki/Q784232","display_name":"Query plan","level":5,"score":0.5744737982749939},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5691897869110107},{"id":"https://openalex.org/C70061542","wikidata":"https://www.wikidata.org/wiki/Q989016","display_name":"Distributed database","level":2,"score":0.48667246103286743},{"id":"https://openalex.org/C87117476","wikidata":"https://www.wikidata.org/wiki/Q362383","display_name":"Cardinality (data modeling)","level":2,"score":0.48538100719451904},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38404661417007446},{"id":"https://openalex.org/C192939062","wikidata":"https://www.wikidata.org/wiki/Q104840822","display_name":"Sargable","level":4,"score":0.3171064853668213},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.303754985332489},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.16998541355133057},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.16193222999572754},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.09516113996505737},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2311.14311","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2311.14311","pdf_url":"https://arxiv.org/pdf/2311.14311","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2311.14311","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2311.14311","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2311.14311","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2311.14311","pdf_url":"https://arxiv.org/pdf/2311.14311","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.5600000023841858,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4389072944.pdf","grobid_xml":"https://content.openalex.org/works/W4389072944.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2006459955","https://openalex.org/W2941854747","https://openalex.org/W1977331029","https://openalex.org/W2955368753","https://openalex.org/W4361194359","https://openalex.org/W203907944","https://openalex.org/W3125756434","https://openalex.org/W1608254253","https://openalex.org/W4386051213","https://openalex.org/W2370317274"],"abstract_inverted_index":{"Selecting":[0],"appropriate":[1],"distributed":[2,41,71,127,140,156],"join":[3,7,42,72,76,107,128,157],"methods":[4,73,158],"for":[5,15,69,149,159],"logical":[6,160],"operations":[8],"in":[9,27,78,91,134,180],"a":[10,66],"query":[11,47,166,191],"plan":[12],"is":[13,137],"crucial":[14],"the":[16,28,40,51,60,85,98,113,116,120,164,172,183,189],"performance":[17],"of":[18,103,115,119,182],"data-intensive":[19],"scalable":[20],"computing":[21,53,89],"(DISC).":[22],"Different":[23],"network":[24,34,61,86],"communication":[25,35,62],"patterns":[26],"data":[29,141],"exchange":[30],"phase":[31],"generate":[32],"varying":[33],"workloads":[36,90],"and":[37,55,87,100,105,153,186],"significantly":[38],"affect":[39],"performance.":[43],"However,":[44],"most":[45],"cost-based":[46],"optimizers":[48],"focus":[49],"on":[50,97,171],"local":[52,88],"cost":[54,67,110,151],"do":[56],"not":[57],"precisely":[58,83],"model":[59,68,111],"cost.":[63],"We":[64,123],"propose":[65],"various":[70],"to":[74,162],"optimize":[75,163],"queries":[77,185],"DISC":[79],"platforms.":[80],"Our":[81,109],"method":[82],"measures":[84],"different":[92],"execution":[93],"phases,":[94],"using":[95],"information":[96],"size":[99,118],"cardinality":[101],"statistics":[102,148],"datasets":[104],"cluster":[106],"parallelism.":[108],"reveals":[112],"importance":[114],"relative":[117],"joining":[121],"datasets.":[122],"implement":[124],"an":[125,138],"efficient":[126],"selection":[129],"strategy,":[130],"known":[131],"as":[132],"RelJoin":[133,144,177],"SparkSQL,":[135],"which":[136],"industry-prevalent":[139],"processing":[142],"framework.":[143],"uses":[145],"runtime":[146],"adaptive":[147],"accurate":[150],"estimation":[152],"selects":[154],"optimal":[155],"joins":[161],"physical":[165],"plan.":[167],"The":[168],"evaluation":[169],"results":[170],"TPC-DS":[173],"benchmark":[174],"show":[175],"that":[176],"performs":[178],"best":[179],"62":[181],"97":[184],"can":[187],"reduce":[188],"average":[190],"time":[192],"by":[193],"21%":[194],"compared":[195],"with":[196],"other":[197],"strategies.":[198]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}