{"id":"https://openalex.org/W2796483994","doi":"https://doi.org/10.1145/3206333.3206340","title":"Adaptive MapReduce Similarity Joins","display_name":"Adaptive MapReduce Similarity Joins","publication_year":2018,"publication_date":"2018-05-17","ids":{"openalex":"https://openalex.org/W2796483994","doi":"https://doi.org/10.1145/3206333.3206340","mag":"2796483994"},"language":"en","primary_location":{"id":"doi:10.1145/3206333.3206340","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3206333.3206340","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th ACM SIGMOD Workshop on Algorithms and Systems for MapReduce and Beyond","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://pure.itu.dk/portal/da/publications/e8ad7917-4762-40df-930f-dd7ea5fcf067","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006653893","display_name":"Samuel McCauley","orcid":"https://orcid.org/0000-0001-8196-9662"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Samuel McCauley","raw_affiliation_strings":["BARC and IT U. Copenhagen, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BARC and IT U. Copenhagen, Denmark","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019173271","display_name":"Francesco Silvestri","orcid":"https://orcid.org/0000-0003-3441-7413"},"institutions":[{"id":"https://openalex.org/I138689650","display_name":"University of Padua","ror":"https://ror.org/00240q980","country_code":"IT","type":"education","lineage":["https://openalex.org/I138689650"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Francesco Silvestri","raw_affiliation_strings":["University of Padova, Italy","University of Padova Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Padova, Italy","institution_ids":["https://openalex.org/I138689650"]},{"raw_affiliation_string":"University of Padova Italy","institution_ids":["https://openalex.org/I138689650"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"68","issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9994999766349792,"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"}},{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9984999895095825,"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":0.9919000267982483,"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/joins","display_name":"Joins","score":0.9474835395812988},{"id":"https://openalex.org/keywords/locality-sensitive-hashing","display_name":"Locality-sensitive hashing","score":0.7586359977722168},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.7549370527267456},{"id":"https://openalex.org/keywords/join","display_name":"Join (topology)","score":0.7178003191947937},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7108178734779358},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5363200306892395},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.48387229442596436},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.46176356077194214},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.4463139474391937},{"id":"https://openalex.org/keywords/massively-parallel","display_name":"Massively parallel","score":0.43906399607658386},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4044918417930603},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3769189715385437},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.34589308500289917},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.32664135098457336},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17980340123176575},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.1423000693321228},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.13926175236701965},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.11946019530296326},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.09981468319892883}],"concepts":[{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.9474835395812988},{"id":"https://openalex.org/C74270461","wikidata":"https://www.wikidata.org/wiki/Q1625299","display_name":"Locality-sensitive hashing","level":4,"score":0.7586359977722168},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.7549370527267456},{"id":"https://openalex.org/C2776124973","wikidata":"https://www.wikidata.org/wiki/Q3183033","display_name":"Join (topology)","level":2,"score":0.7178003191947937},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7108178734779358},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5363200306892395},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.48387229442596436},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.46176356077194214},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.4463139474391937},{"id":"https://openalex.org/C190475519","wikidata":"https://www.wikidata.org/wiki/Q544384","display_name":"Massively parallel","level":2,"score":0.43906399607658386},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4044918417930603},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3769189715385437},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34589308500289917},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.32664135098457336},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17980340123176575},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.1423000693321228},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13926175236701965},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.11946019530296326},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.09981468319892883},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1145/3206333.3206340","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3206333.3206340","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th ACM SIGMOD Workshop on Algorithms and Systems for MapReduce and Beyond","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:openaire/e8ad7917-4762-40df-930f-dd7ea5fcf067","is_oa":true,"landing_page_url":"https://pure.itu.dk/portal/da/publications/e8ad7917-4762-40df-930f-dd7ea5fcf067","pdf_url":null,"source":{"id":"https://openalex.org/S4377196680","display_name":"IT University Of Copenhagen (IT University of Copenhagen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I83467386","host_organization_name":"IT University of Copenhagen","host_organization_lineage":["https://openalex.org/I83467386"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"McCauley, S & Silvestri, F 2018, Adaptive MapReduce Similarity Joins. in Proceedings of the 5th ACM SIGMOD Workshop on Algorithms and Systems for MapReduce and Beyond : BeyondMR'18. Association for Computing Machinery. https://doi.org/10.1145/3206333.3206340","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:arXiv.org:1804.05615","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1804.05615","pdf_url":"https://arxiv.org/pdf/1804.05615","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":"","raw_type":"text"},{"id":"pmh:oai:www.research.unipd.it:11577/3277697","is_oa":true,"landing_page_url":"http://hdl.handle.net/11577/3277697","pdf_url":"http://hdl.handle.net/11577/3277697","source":{"id":"https://openalex.org/S4377196283","display_name":"Research Padua  Archive (University of Padua)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I138689650","host_organization_name":"University of Padua","host_organization_lineage":["https://openalex.org/I138689650"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"mag:2796483994","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1804.05615","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1804.05615","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1804.05615","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:openaire/e8ad7917-4762-40df-930f-dd7ea5fcf067","is_oa":true,"landing_page_url":"https://pure.itu.dk/portal/da/publications/e8ad7917-4762-40df-930f-dd7ea5fcf067","pdf_url":null,"source":{"id":"https://openalex.org/S4377196680","display_name":"IT University Of Copenhagen (IT University of Copenhagen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I83467386","host_organization_name":"IT University of Copenhagen","host_organization_lineage":["https://openalex.org/I83467386"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"McCauley, S & Silvestri, F 2018, Adaptive MapReduce Similarity Joins. in Proceedings of the 5th ACM SIGMOD Workshop on Algorithms and Systems for MapReduce and Beyond : BeyondMR'18. Association for Computing Machinery. https://doi.org/10.1145/3206333.3206340","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4422840520","display_name":null,"funder_award_id":"16582","funder_id":"https://openalex.org/F4320310490","funder_display_name":"Villum Fonden"},{"id":"https://openalex.org/G6396797479","display_name":null,"funder_award_id":"614331","funder_id":"https://openalex.org/F4320338335","funder_display_name":"H2020 European Research Council"},{"id":"https://openalex.org/G7921004072","display_name":null,"funder_award_id":"SID2017","funder_id":"https://openalex.org/F4320321966","funder_display_name":"Universit\u00e0 degli Studi di Padova"},{"id":"https://openalex.org/G8079901054","display_name":"Hawaiian Workshop on Parallel Algorithms and Data Structures","funder_award_id":"1745331","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320310490","display_name":"Villum Fonden","ror":"https://ror.org/007ww2d15"},{"id":"https://openalex.org/F4320321966","display_name":"Universit\u00e0 degli Studi di Padova","ror":"https://ror.org/00240q980"},{"id":"https://openalex.org/F4320334966","display_name":"Bhabha Atomic Research Centre","ror":"https://ror.org/05w6wfp17"},{"id":"https://openalex.org/F4320338335","display_name":"H2020 European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1998067572","https://openalex.org/W2008199814","https://openalex.org/W2040660972","https://openalex.org/W2045271686","https://openalex.org/W2051586153","https://openalex.org/W2096598900","https://openalex.org/W2097776316","https://openalex.org/W2152565070","https://openalex.org/W2597017779","https://openalex.org/W2604241689","https://openalex.org/W2604829000","https://openalex.org/W2612210001","https://openalex.org/W2778604241","https://openalex.org/W2952870688","https://openalex.org/W2963886823","https://openalex.org/W3104626761","https://openalex.org/W6735331192","https://openalex.org/W6735888442"],"related_works":["https://openalex.org/W2604829000","https://openalex.org/W980041598","https://openalex.org/W3099795033","https://openalex.org/W2963886823","https://openalex.org/W2897158376","https://openalex.org/W2150916025","https://openalex.org/W2356914479","https://openalex.org/W2751997091","https://openalex.org/W1488303220","https://openalex.org/W2903672378","https://openalex.org/W2951438725","https://openalex.org/W2900972923","https://openalex.org/W2950817225","https://openalex.org/W3012776781","https://openalex.org/W2584499795","https://openalex.org/W2798412430","https://openalex.org/W2611719484","https://openalex.org/W2151596444","https://openalex.org/W2250382098","https://openalex.org/W2039797165"],"abstract_inverted_index":{"Similarity":[0],"joins":[1,73],"are":[2],"a":[3,16,75,98],"fundamental":[4],"database":[5],"operation.":[6],"Given":[7],"data":[8],"sets":[9],"S":[10,26],"and":[11,27,50,68,93],"R,":[12],"the":[13,85,88,104,107,113],"goal":[14],"of":[15,56,87,106],"similarity":[17,48],"join":[18,64],"is":[19],"to":[20,84,103],"find":[21],"all":[22],"points":[23],"x":[24],"\u2208":[25,29],"y":[28],"R":[30],"with":[31],"distance":[32],"at":[33],"most":[34],"r.":[35],"Recent":[36],"research":[37],"has":[38],"investigated":[39,72],"how":[40],"locality-sensitive":[41],"hashing":[42],"(LSH)":[43],"can":[44],"be":[45],"used":[46],"for":[47],"join,":[49],"in":[51,74,112],"particular":[52],"two":[53],"recent":[54],"lines":[55],"work":[57],"have":[58],"made":[59],"exciting":[60],"progress":[61],"on":[62,120],"LSH-based":[63],"performance.":[65],"Hu,":[66],"Tao,":[67],"Yi":[69],"(PODS":[70],"17)":[71,96],"massively":[76],"parallel":[77],"setting,":[78],"showing":[79],"strong":[80],"results":[81],"that":[82,101],"adapt":[83],"size":[86],"output.":[89],"Meanwhile,":[90],"Ahle,":[91],"Aum\u00fcller,":[92],"Pagh":[94],"(SODA":[95],"showed":[97],"sequential":[99],"algorithm":[100],"adapts":[102],"structure":[105],"data,":[108],"matching":[109],"classic":[110],"bounds":[111],"worst":[114],"case":[115],"but":[116],"improving":[117],"them":[118],"significantly":[119],"more":[121],"structured":[122],"data.":[123]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}