{"id":"https://openalex.org/W3015629709","doi":"https://doi.org/10.1145/3318464.3389750","title":"Near-Optimal Distributed Band-Joins through Recursive Partitioning","display_name":"Near-Optimal Distributed Band-Joins through Recursive Partitioning","publication_year":2020,"publication_date":"2020-05-29","ids":{"openalex":"https://openalex.org/W3015629709","doi":"https://doi.org/10.1145/3318464.3389750","mag":"3015629709","pmid":"https://pubmed.ncbi.nlm.nih.gov/33568887"},"language":"en","primary_location":{"id":"doi:10.1145/3318464.3389750","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3318464.3389750","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 ACM SIGMOD International Conference on Management of Data","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2004.06101","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101780303","display_name":"Rundong Li","orcid":"https://orcid.org/0000-0003-0354-9536"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Rundong Li","raw_affiliation_strings":["Google, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086781628","display_name":"Wolfgang Gatterbauer","orcid":"https://orcid.org/0000-0002-9614-0504"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wolfgang Gatterbauer","raw_affiliation_strings":["Northeastern University, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049802784","display_name":"Mirek Riedewald","orcid":"https://orcid.org/0000-0002-6102-7472"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mirek Riedewald","raw_affiliation_strings":["Northeastern University, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101780303"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":2.2251,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.90459553,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"2020","issue":null,"first_page":"2375","last_page":"2390"},"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":0.9977999925613403,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/joins","display_name":"Joins","score":0.9839725494384766},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7712236642837524},{"id":"https://openalex.org/keywords/join","display_name":"Join (topology)","score":0.6757215261459351},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.5870609283447266},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.57451993227005},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.470790296792984},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.42842280864715576},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.363023042678833},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.32499960064888},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14942297339439392},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08079919219017029}],"concepts":[{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.9839725494384766},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7712236642837524},{"id":"https://openalex.org/C2776124973","wikidata":"https://www.wikidata.org/wiki/Q3183033","display_name":"Join (topology)","level":2,"score":0.6757215261459351},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.5870609283447266},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.57451993227005},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.470790296792984},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.42842280864715576},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.363023042678833},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.32499960064888},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14942297339439392},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08079919219017029},{"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/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3318464.3389750","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3318464.3389750","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 ACM SIGMOD International Conference on Management of Data","raw_type":"proceedings-article"},{"id":"pmid:33568887","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33568887","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. ACM-SIGMOD International Conference on Management of Data","raw_type":null},{"id":"pmh:oai:arXiv.org:2004.06101","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.06101","pdf_url":"https://arxiv.org/pdf/2004.06101","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:pubmedcentral.nih.gov:7872589","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7872589","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proc ACM SIGMOD Int Conf Manag Data","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2004.06101","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.06101","pdf_url":"https://arxiv.org/pdf/2004.06101","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.6399999856948853,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[{"id":"https://openalex.org/G5139550722","display_name":null,"funder_award_id":"R01 NS091421","funder_id":"https://openalex.org/F4320306080","funder_display_name":"Foundation for the National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320306080","display_name":"Foundation for the National Institutes of Health","ror":"https://ror.org/00k86s890"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1487093789","https://openalex.org/W1497089183","https://openalex.org/W1497100682","https://openalex.org/W1500547548","https://openalex.org/W1520750340","https://openalex.org/W1554177507","https://openalex.org/W1570320352","https://openalex.org/W1574862731","https://openalex.org/W1581547316","https://openalex.org/W1585614323","https://openalex.org/W1597532222","https://openalex.org/W1756474508","https://openalex.org/W1973898816","https://openalex.org/W1993226606","https://openalex.org/W2007030756","https://openalex.org/W2011078029","https://openalex.org/W2011129635","https://openalex.org/W2037027334","https://openalex.org/W2043099794","https://openalex.org/W2047529508","https://openalex.org/W2051244613","https://openalex.org/W2061601738","https://openalex.org/W2078528123","https://openalex.org/W2113463961","https://openalex.org/W2119783318","https://openalex.org/W2131724164","https://openalex.org/W2137373960","https://openalex.org/W2148838171","https://openalex.org/W2171903035","https://openalex.org/W2173213060","https://openalex.org/W2189465200","https://openalex.org/W2261815431","https://openalex.org/W2270660075","https://openalex.org/W2277471751","https://openalex.org/W2435648513","https://openalex.org/W2440979603","https://openalex.org/W2512795599","https://openalex.org/W2526315256","https://openalex.org/W2770089293","https://openalex.org/W2799137389","https://openalex.org/W2883952940","https://openalex.org/W2888254789","https://openalex.org/W2923924305","https://openalex.org/W3015629709","https://openalex.org/W3099336511"],"related_works":["https://openalex.org/W2393491644","https://openalex.org/W650102067","https://openalex.org/W4206577045","https://openalex.org/W3086237447","https://openalex.org/W1550806730","https://openalex.org/W2589740103","https://openalex.org/W3033055359","https://openalex.org/W2172084996","https://openalex.org/W1966967794","https://openalex.org/W1501284171"],"abstract_inverted_index":{"We":[0,27],"consider":[1],"running-time":[2],"optimization":[3,52,87],"for":[4,42,103,108,131,140],"band-joins":[5,43,105],"in":[6,62],"a":[7,141],"distributed":[8],"system,":[9],"e.g.,":[10],"the":[11,74,78,95,128],"cloud.":[12],"To":[13],"balance":[14],"load":[15,36,134],"across":[16],"worker":[17,136],"machines,":[18],"input":[19,138],"has":[20],"to":[21,30,120],"be":[22],"partitioned,":[23],"which":[24],"causes":[25],"duplication.":[26],"explore":[28],"how":[29],"resolve":[31],"this":[32],"tension":[33],"between":[34,44],"<i>maximum":[35],"per":[37,135],"worker</i>":[38],"and":[39,89,137],"<i>input":[40],"duplication</i>":[41],"two":[45],"relations.":[46],"Previous":[47],"work":[48],"suffered":[49],"from":[50],"high":[51],"cost":[53,88],"or":[54],"considered":[55],"partitionings":[56,122],"that":[57,70,98,115,123],"were":[58],"too":[59],"restricted":[60],"(resulting":[61],"suboptimal":[63],"join":[64,91],"performance).":[65],"Our":[66],"main":[67],"insight":[68],"is":[69,94,99,118],"<i>recursive":[71],"partitioning":[72],"of":[73,127,144],"join-attribute":[75],"space</i>":[76],"with":[77],"appropriate":[79],"split":[80],"scoring":[81],"measure":[82],"can":[83],"achieve":[84],"both":[85,132],"low":[86,90],"cost.":[92],"It":[93],"first":[96],"approach":[97],"not":[100],"only":[101],"effective":[102],"one-dimensional":[104],"but":[106],"also":[107],"joins":[109],"on":[110],"multiple":[111],"attributes.":[112],"Experiments":[113],"indicate":[114],"our":[116],"method":[117],"able":[119],"find":[121],"are":[124],"within":[125],"10%":[126],"<i>lower":[129],"bound</i>":[130],"maximum":[133],"duplication":[139],"broad":[142],"range":[143],"settings,":[145],"significantly":[146],"improving":[147],"over":[148],"previous":[149],"work.":[150]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}