{"id":"https://openalex.org/W2151930506","doi":"https://doi.org/10.1145/1807167.1807222","title":"Efficient parallel set-similarity joins using MapReduce","display_name":"Efficient parallel set-similarity joins using MapReduce","publication_year":2010,"publication_date":"2010-06-06","ids":{"openalex":"https://openalex.org/W2151930506","doi":"https://doi.org/10.1145/1807167.1807222","mag":"2151930506"},"language":"en","primary_location":{"id":"doi:10.1145/1807167.1807222","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1807167.1807222","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2010 ACM SIGMOD International Conference on Management of data","raw_type":"proceedings-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/A5007859752","display_name":"Rares Vernica","orcid":null},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Rares Vernica","raw_affiliation_strings":["University of California, Irvine, Irvine, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Irvine, Irvine, CA, USA","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011512061","display_name":"Michael J. Carey","orcid":"https://orcid.org/0000-0003-1561-4059"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael J. Carey","raw_affiliation_strings":["University of California, Irvine, Irvine, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Irvine, Irvine, CA, USA","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100369885","display_name":"Chen Li","orcid":"https://orcid.org/0000-0002-8784-8148"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen Li","raw_affiliation_strings":["University of California, Irvine, Irvine, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Irvine, Irvine, CA, USA","institution_ids":["https://openalex.org/I204250578"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5007859752"],"corresponding_institution_ids":["https://openalex.org/I204250578"],"apc_list":null,"apc_paid":null,"fwci":57.2294,"has_fulltext":false,"cited_by_count":456,"citation_normalized_percentile":{"value":0.99955949,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"495","last_page":"506"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9991000294685364,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9976999759674072,"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/joins","display_name":"Joins","score":0.937859833240509},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8532131910324097},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6415425539016724},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6369826793670654},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6175698041915894},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.5782430171966553},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.5571258664131165},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5373742580413818},{"id":"https://openalex.org/keywords/join","display_name":"Join (topology)","score":0.5195186734199524},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.4857959747314453},{"id":"https://openalex.org/keywords/replication","display_name":"Replication (statistics)","score":0.43820780515670776},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.43690332770347595},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.43156737089157104},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.36203256249427795},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1498585045337677},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.101769357919693},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.06762149930000305}],"concepts":[{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.937859833240509},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8532131910324097},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6415425539016724},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6369826793670654},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6175698041915894},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.5782430171966553},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.5571258664131165},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5373742580413818},{"id":"https://openalex.org/C2776124973","wikidata":"https://www.wikidata.org/wiki/Q3183033","display_name":"Join (topology)","level":2,"score":0.5195186734199524},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.4857959747314453},{"id":"https://openalex.org/C12590798","wikidata":"https://www.wikidata.org/wiki/Q3933199","display_name":"Replication (statistics)","level":2,"score":0.43820780515670776},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.43690332770347595},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.43156737089157104},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.36203256249427795},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1498585045337677},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.101769357919693},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.06762149930000305},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/1807167.1807222","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1807167.1807222","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2010 ACM SIGMOD International Conference on Management of data","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.170.1308","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.170.1308","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ics.uci.edu/%7Ervernica/pub/sigmod10-p495-vernica.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.174.2778","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.174.2778","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://asterix.ics.uci.edu/pub/sigmod10-p495-vernica-long.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.188.551","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.188.551","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ics.uci.edu/%7Ervernica/pub/sigmod10-vernica.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1500547548","https://openalex.org/W1502916507","https://openalex.org/W1585614323","https://openalex.org/W1997020216","https://openalex.org/W2007030756","https://openalex.org/W2078528123","https://openalex.org/W2085922539","https://openalex.org/W2096598900","https://openalex.org/W2097184821","https://openalex.org/W2097776316","https://openalex.org/W2099194763","https://openalex.org/W2114303224","https://openalex.org/W2114353347","https://openalex.org/W2121516976","https://openalex.org/W2127675794","https://openalex.org/W2142031898","https://openalex.org/W2150916025","https://openalex.org/W2151930506","https://openalex.org/W2152565070","https://openalex.org/W2154894831","https://openalex.org/W2161443453","https://openalex.org/W2161936973","https://openalex.org/W2164634022","https://openalex.org/W2173213060","https://openalex.org/W4238594802","https://openalex.org/W6629856530","https://openalex.org/W6629956336","https://openalex.org/W6674576723","https://openalex.org/W6683401941"],"related_works":["https://openalex.org/W2393491644","https://openalex.org/W4206577045","https://openalex.org/W3086237447","https://openalex.org/W650102067","https://openalex.org/W2740404111","https://openalex.org/W1550806730","https://openalex.org/W1496672428","https://openalex.org/W2589740103","https://openalex.org/W1966967794","https://openalex.org/W1501284171"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3,101],"study":[4,67],"how":[5,76],"to":[6,56,77,133],"efficiently":[7,48],"perform":[8],"set-similarity":[9,25,45],"joins":[10],"in":[11,54,85,113,131],"parallel":[12],"using":[13,144],"the":[14,50,58,62,80,96,103,107,114,135,141],"popular":[15],"MapReduce":[16],"framework.":[17],"We":[18,27,47,66,91,120],"propose":[19,93],"a":[20,31,37,44,118],"3-stage":[21],"approach":[22],"for":[23,64,95],"end-to-end":[24],"joins.":[26],"take":[28],"as":[29],"input":[30],"set":[32,38],"of":[33,39,82,117,140],"records":[34,41],"and":[35,60,70,74,137],"output":[36],"joined":[40],"based":[42],"on":[43,88,126],"condition.":[46],"partition":[49],"data":[51,83,108],"across":[52],"nodes":[53],"order":[55],"balance":[57],"workload":[59],"minimize":[61],"need":[63],"replication.":[65],"both":[68],"self-join":[69],"R-S":[71],"join":[72],"cases,":[73],"show":[75],"carefully":[78],"control":[79],"amount":[81],"kept":[84],"main":[86,115],"memory":[87,116],"each":[89],"node.":[90,119],"also":[92],"solutions":[94],"case":[97],"where,":[98],"even":[99],"if":[100],"use":[102],"most":[104],"fine-grained":[105],"partitioning,":[106],"still":[109],"does":[110],"not":[111],"fit":[112],"report":[121],"results":[122],"from":[123],"extensive":[124],"experiments":[125],"real":[127],"datasets,":[128],"synthetically":[129],"increased":[130],"size,":[132],"evaluate":[134],"speedup":[136],"scaleup":[138],"properties":[139],"proposed":[142],"algorithms":[143],"Hadoop.":[145]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":21},{"year":2020,"cited_by_count":21},{"year":2019,"cited_by_count":35},{"year":2018,"cited_by_count":34},{"year":2017,"cited_by_count":26},{"year":2016,"cited_by_count":40},{"year":2015,"cited_by_count":49},{"year":2014,"cited_by_count":58},{"year":2013,"cited_by_count":55},{"year":2012,"cited_by_count":45}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}