{"id":"https://openalex.org/W2163051926","doi":"https://doi.org/10.1145/2463676.2465280","title":"Leveraging transitive relations for crowdsourced joins","display_name":"Leveraging transitive relations for crowdsourced joins","publication_year":2013,"publication_date":"2013-06-22","ids":{"openalex":"https://openalex.org/W2163051926","doi":"https://doi.org/10.1145/2463676.2465280","mag":"2163051926"},"language":"en","primary_location":{"id":"doi:10.1145/2463676.2465280","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2463676.2465280","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2013 ACM SIGMOD International Conference on Management of Data","raw_type":"proceedings-article"},"type":"preprint","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/A5101850961","display_name":"Jiannan Wang","orcid":"https://orcid.org/0009-0002-8978-312X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiannan Wang","raw_affiliation_strings":["Department of Computer Science, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100451576","display_name":"Guoliang Li","orcid":"https://orcid.org/0000-0002-1398-0621"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoliang Li","raw_affiliation_strings":["Department of Computer Science, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034086130","display_name":"Tim Kraska","orcid":"https://orcid.org/0009-0003-2414-2759"},"institutions":[{"id":"https://openalex.org/I27804330","display_name":"Brown University","ror":"https://ror.org/05gq02987","country_code":"US","type":"education","lineage":["https://openalex.org/I27804330"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tim Kraska","raw_affiliation_strings":["Brown University, Providence, USA"],"affiliations":[{"raw_affiliation_string":"Brown University, Providence, USA","institution_ids":["https://openalex.org/I27804330"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102019638","display_name":"Michael J. Franklin","orcid":"https://orcid.org/0000-0003-3332-8574"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael J. Franklin","raw_affiliation_strings":["AMPLab, UC Berkeley, Berkeley, USA"],"affiliations":[{"raw_affiliation_string":"AMPLab, UC Berkeley, Berkeley, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100951661","display_name":"Jianhua Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianhua Feng","raw_affiliation_strings":["Department of Computer Science, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101850961"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":35.9742,"has_fulltext":false,"cited_by_count":208,"citation_normalized_percentile":{"value":0.99706103,"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":"229","last_page":"240"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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"}}],"keywords":[{"id":"https://openalex.org/keywords/crowdsourcing","display_name":"Crowdsourcing","score":0.879626989364624},{"id":"https://openalex.org/keywords/transitive-relation","display_name":"Transitive relation","score":0.815534234046936},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8144664764404297},{"id":"https://openalex.org/keywords/joins","display_name":"Joins","score":0.7884397506713867},{"id":"https://openalex.org/keywords/transitive-closure","display_name":"Transitive closure","score":0.7083685994148254},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6556559801101685},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5488600730895996},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5052376389503479},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3702489733695984},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.353310763835907},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.35296154022216797},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.34908467531204224},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.21180805563926697},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09851402044296265},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08238023519515991}],"concepts":[{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.879626989364624},{"id":"https://openalex.org/C191399111","wikidata":"https://www.wikidata.org/wiki/Q64861","display_name":"Transitive relation","level":2,"score":0.815534234046936},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8144664764404297},{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.7884397506713867},{"id":"https://openalex.org/C128896722","wikidata":"https://www.wikidata.org/wiki/Q1501387","display_name":"Transitive closure","level":2,"score":0.7083685994148254},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6556559801101685},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5488600730895996},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5052376389503479},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3702489733695984},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.353310763835907},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35296154022216797},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34908467531204224},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.21180805563926697},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09851402044296265},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08238023519515991},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/2463676.2465280","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2463676.2465280","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2013 ACM SIGMOD International Conference on Management of Data","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.357.2208","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.357.2208","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://dbgroup.cs.tsinghua.edu.cn/ligl/papers/sigmod13-transitivity.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.722.5970","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.722.5970","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.berkeley.edu/%7Ejnwang/papers/sigmod2013-crowder-transitivity.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W82775311","https://openalex.org/W284823514","https://openalex.org/W1569123402","https://openalex.org/W1974554406","https://openalex.org/W1977810318","https://openalex.org/W1986022261","https://openalex.org/W1988511622","https://openalex.org/W2028818097","https://openalex.org/W2053653724","https://openalex.org/W2056748234","https://openalex.org/W2058179030","https://openalex.org/W2066640191","https://openalex.org/W2069897123","https://openalex.org/W2076357412","https://openalex.org/W2083293881","https://openalex.org/W2098865355","https://openalex.org/W2101620066","https://openalex.org/W2106675345","https://openalex.org/W2113878109","https://openalex.org/W2117974736","https://openalex.org/W2145492473","https://openalex.org/W2148479118","https://openalex.org/W2168144930","https://openalex.org/W2225677724","https://openalex.org/W2400013274","https://openalex.org/W2914959486","https://openalex.org/W4230939871","https://openalex.org/W6603353687","https://openalex.org/W6663798068"],"related_works":["https://openalex.org/W1553139688","https://openalex.org/W2371151875","https://openalex.org/W2136009070","https://openalex.org/W2362009423","https://openalex.org/W2391133415","https://openalex.org/W2012063573","https://openalex.org/W1982015164","https://openalex.org/W203725150","https://openalex.org/W4230967508","https://openalex.org/W1499233953"],"abstract_inverted_index":{"The":[0],"development":[1],"of":[2,19,44,71,175],"crowdsourced":[3,20,32,157],"query":[4,34],"processing":[5],"systems":[6],"has":[7],"recently":[8],"attracted":[9],"a":[10,51,58,68,104,161,191,212,236],"significant":[11],"attention":[12],"in":[13,82,207,239],"the":[14,31,80,83,92,110,113,172,180,185,198,201,240],"database":[15],"community.":[16],"A":[17],"variety":[18],"queries":[21],"have":[22],"been":[23],"investigated.":[24],"In":[25],"this":[26,147],"paper,":[27],"we":[28,56,132,149],"focus":[29],"on":[30],"join":[33],"which":[35,62,168],"aims":[36,169],"to":[37,40,66,78,103,142,152,170,177,195],"utilize":[38],"humans":[39,77],"find":[41],"all":[42,99,179],"pairs":[43,81,100,114,176,199],"matching":[45,72,88],"objects":[46],"from":[47],"two":[48],"collections.":[49],"As":[50,118],"human-only":[52],"solution":[53],"is":[54],"expensive,":[55],"adopt":[57],"hybrid":[59,162],"human-machine":[60],"approach":[61],"first":[63],"uses":[64],"machines":[65],"generate":[67],"candidate":[69,84,93,181],"set":[70,85],"pairs,":[73,94],"and":[74,126,164,189,211,230],"then":[75,131],"asks":[76],"label":[79,178],"as":[86],"either":[87],"or":[89],"non-matching.":[90],"Given":[91],"existing":[95,233],"approaches":[96,206,221],"will":[97],"publish":[98],"for":[101,156],"verification":[102],"crowdsourcing":[105,165,214],"platform.":[106,215],"However,":[107],"they":[108],"neglect":[109],"fact":[111],"that":[112,135,219],"satisfy":[115],"transitive":[116,154,223],"relations.":[117],"an":[119],"example,":[120],"if":[121],"o1":[122,136],"matches":[123,128,137],"with":[124,129,138,222,235],"o2,":[125],"o2":[127],"o3,":[130],"can":[133,225],"deduce":[134],"o3":[139],"without":[140],"needing":[141],"crowdsource":[143,171,197],"(o1,":[144],"o3).":[145],"To":[146],"end,":[148],"study":[150],"how":[151],"leverage":[153],"relations":[155,224],"joins.":[158],"We":[159,183,203],"propose":[160],"transitive-relations":[163],"labeling":[166,187,193],"framework":[167],"minimum":[173],"number":[174],"pairs.":[182],"prove":[184],"optimal":[186],"order":[188],"devise":[190],"parallel":[192],"algorithm":[194],"efficiently":[196],"following":[200],"order.":[202],"evaluate":[204],"our":[205,220],"both":[208],"simulated":[209],"environment":[210],"real":[213],"Experimental":[216],"results":[217],"show":[218],"save":[226],"much":[227],"more":[228],"money":[229],"time":[231],"than":[232],"methods,":[234],"little":[237],"loss":[238],"result":[241],"quality.":[242]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":21},{"year":2020,"cited_by_count":20},{"year":2019,"cited_by_count":16},{"year":2018,"cited_by_count":34},{"year":2017,"cited_by_count":32},{"year":2016,"cited_by_count":24},{"year":2015,"cited_by_count":24},{"year":2014,"cited_by_count":17},{"year":2013,"cited_by_count":4}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}