{"id":"https://openalex.org/W2798412430","doi":"https://doi.org/10.1145/3183713.3183748","title":"Overlap Set Similarity Joins with Theoretical Guarantees","display_name":"Overlap Set Similarity Joins with Theoretical Guarantees","publication_year":2018,"publication_date":"2018-05-25","ids":{"openalex":"https://openalex.org/W2798412430","doi":"https://doi.org/10.1145/3183713.3183748","mag":"2798412430"},"language":"en","primary_location":{"id":"doi:10.1145/3183713.3183748","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3183713.3183748","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 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/A5103237059","display_name":"Dong Deng","orcid":"https://orcid.org/0000-0002-4596-3850"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Dong Deng","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048609852","display_name":"Yufei Tao","orcid":"https://orcid.org/0000-0003-3883-5452"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yufei Tao","raw_affiliation_strings":["Chinese University of Hong Kong, Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Chinese University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","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":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5103237059"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":6.9878,"has_fulltext":false,"cited_by_count":45,"citation_normalized_percentile":{"value":0.97063715,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"905","last_page":"920"},"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":0.992900013923645,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9763000011444092,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/joins","display_name":"Joins","score":0.7452716827392578},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.7240949273109436},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7060990333557129},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6106219291687012},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5598747730255127},{"id":"https://openalex.org/keywords/boundary","display_name":"Boundary (topology)","score":0.4609743654727936},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4592783749103546},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4508107900619507},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.33755767345428467},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3332101106643677},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21825888752937317},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2086866796016693}],"concepts":[{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.7452716827392578},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.7240949273109436},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7060990333557129},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6106219291687012},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5598747730255127},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.4609743654727936},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4592783749103546},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4508107900619507},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33755767345428467},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3332101106643677},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21825888752937317},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2086866796016693},{"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3183713.3183748","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3183713.3183748","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 International Conference on Management of Data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1455310343","https://openalex.org/W1502916507","https://openalex.org/W1575370549","https://openalex.org/W1768336749","https://openalex.org/W1973001156","https://openalex.org/W1977046819","https://openalex.org/W1978400666","https://openalex.org/W1981617416","https://openalex.org/W1991175610","https://openalex.org/W2010454887","https://openalex.org/W2037562342","https://openalex.org/W2065259291","https://openalex.org/W2073112656","https://openalex.org/W2096598900","https://openalex.org/W2097776316","https://openalex.org/W2105436061","https://openalex.org/W2121269638","https://openalex.org/W2121516976","https://openalex.org/W2127675794","https://openalex.org/W2152184085","https://openalex.org/W2152565070","https://openalex.org/W2153579005","https://openalex.org/W2156855109","https://openalex.org/W2166400748","https://openalex.org/W2167847032","https://openalex.org/W2169054943","https://openalex.org/W2218762779","https://openalex.org/W2250539671","https://openalex.org/W2261895596","https://openalex.org/W2294222380","https://openalex.org/W2294331997","https://openalex.org/W2396588571","https://openalex.org/W2397770138","https://openalex.org/W2615445578","https://openalex.org/W2619410666","https://openalex.org/W2950133940","https://openalex.org/W2962863202","https://openalex.org/W3105727767","https://openalex.org/W6629956336","https://openalex.org/W6638104246","https://openalex.org/W6674576723"],"related_works":["https://openalex.org/W2088925915","https://openalex.org/W2382891957","https://openalex.org/W2393491644","https://openalex.org/W2067184662","https://openalex.org/W3047837489","https://openalex.org/W2622139626","https://openalex.org/W2133660117","https://openalex.org/W2104496206","https://openalex.org/W3013303285","https://openalex.org/W2385836742"],"abstract_inverted_index":{"This":[0,36],"paper":[1],"studies":[2],"the":[3,23,27,65,70,81,94,103,125,131,143,148,153,157,161,167,204],"set":[4,24],"similarity":[5],"join":[6],"problem":[7],"with":[8,80],"overlap":[9],"constraints":[10],"which,":[11],"given":[12],"two":[13],"collections":[14],"of":[15,56,68,84,96,212],"sets":[16,104,127,133,145,159,163],"and":[17,50,107,114,128,160,202],"a":[18,38,77],"constant":[19],"c,":[20],"finds":[21],"all":[22,57,69,102],"pairs":[25],"in":[26,41,134,188],"datasets":[28,194],"that":[29,196],"share":[30],"at":[31],"least":[32],"c":[33,87],"common":[34],"elements.":[35],"is":[37,60,64,93,164],"fundamental":[39],"operation":[40],"many":[42],"fields,":[43],"such":[44],"as":[45],"information":[46],"retrieval,":[47],"data":[48],"mining,":[49],"machine":[51],"learning.":[52],"The":[53,98],"time":[54,82],"complexity":[55,83],"existing":[58,121],"methods":[59,122,198],"O(n2)":[61],"where":[62,91],"n":[63],"total":[66],"size":[67,154,173,182],"sets.":[71],"In":[72],"this":[73,135],"paper,":[74],"we":[75,169],"present":[76],"size-aware":[78,99],"algorithm":[79,100,176],"O(n2-over":[85],"1":[86],"k1":[88],"over":[89],"2c)=o(n2)+O(k),":[90],"k":[92],"number":[95],"results.":[97],"divides":[101],"into":[105],"small":[106,132,144,158],"large":[108,126,162],"ones":[109],"based":[110],"on":[111,130,192],"their":[112],"sizes":[113],"processes":[115],"them":[116],"separately.":[117],"We":[118,137],"can":[119],"use":[120],"to":[123,146,166,177,209],"process":[124],"focus":[129],"paper.":[136],"develop":[138],"several":[139],"optimization":[140],"heuristics":[141],"for":[142],"improve":[147],"practical":[149],"performance":[150,201],"significantly.":[151],"As":[152],"boundary":[155,174],"between":[156],"crucial":[165],"efficiency,":[168],"propose":[170],"an":[171,180,210],"effective":[172],"selection":[175],"judiciously":[178],"choose":[179],"appropriate":[181],"boundary,":[183],"which":[184],"works":[185],"very":[186],"well":[187],"practice.":[189],"Experimental":[190],"results":[191],"real-world":[193],"show":[195],"our":[197],"achieve":[199],"high":[200],"outperform":[203],"state-of-the-art":[205],"approaches":[206],"by":[207],"up":[208],"order":[211],"magnitude.":[213]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}