{"id":"https://openalex.org/W2964953836","doi":"https://doi.org/10.1145/3292500.3330853","title":"MinJoin","display_name":"MinJoin","publication_year":2019,"publication_date":"2019-07-25","ids":{"openalex":"https://openalex.org/W2964953836","doi":"https://doi.org/10.1145/3292500.3330853","mag":"2964953836"},"language":"en","primary_location":{"id":"doi:10.1145/3292500.3330853","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3292500.3330853","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3292500.3330853","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3292500.3330853","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100425890","display_name":"Haoyu Zhang","orcid":"https://orcid.org/0000-0002-6225-647X"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Haoyu Zhang","raw_affiliation_strings":["Indiana University Bloomington, Bloomginton, IN, USA"],"affiliations":[{"raw_affiliation_string":"Indiana University Bloomington, Bloomginton, IN, USA","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100418224","display_name":"Qin Zhang","orcid":"https://orcid.org/0000-0002-6851-3115"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qin Zhang","raw_affiliation_strings":["Indiana University Bloomington, Bloomginton, IN, USA"],"affiliations":[{"raw_affiliation_string":"Indiana University Bloomington, Bloomginton, IN, USA","institution_ids":["https://openalex.org/I4210119109"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100425890"],"corresponding_institution_ids":["https://openalex.org/I4210119109"],"apc_list":null,"apc_paid":null,"fwci":1.856,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":{"value":0.86529467,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1093","last_page":"1103"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"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":0.9998999834060669,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9957000017166138,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9955000281333923,"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":0.9026841521263123},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7832558155059814},{"id":"https://openalex.org/keywords/edit-distance","display_name":"Edit distance","score":0.7811733484268188},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6840587854385376},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5055446624755859},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4957369267940521},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4380091726779938},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4192420244216919},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2719331979751587},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23648440837860107},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09202802181243896}],"concepts":[{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.9026841521263123},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7832558155059814},{"id":"https://openalex.org/C44359876","wikidata":"https://www.wikidata.org/wiki/Q5338467","display_name":"Edit distance","level":2,"score":0.7811733484268188},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6840587854385376},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5055446624755859},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4957369267940521},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4380091726779938},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4192420244216919},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2719331979751587},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23648440837860107},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09202802181243896},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3292500.3330853","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3292500.3330853","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3292500.3330853","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3292500.3330853","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3292500.3330853","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3292500.3330853","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5400000214576721,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G1028924556","display_name":"CAREER:Foundation of Communication-Efficient Distributed Computation and Monitoring","funder_award_id":"1844234","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3543361024","display_name":null,"funder_award_id":"CCF-1525024, IIS-1633215","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4238407609","display_name":"BIGDATA: Collaborative Research: F: Efficient Distributed Computation of Large-Scale Graph Problems in Epidemiology and Contagion Dynamics","funder_award_id":"1633215","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4527037313","display_name":null,"funder_award_id":"CCF-1525024","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5215040369","display_name":null,"funder_award_id":"IIS-1633215","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7980180814","display_name":null,"funder_award_id":"CCF-1525024, IIS-1633215, CCF-1844234","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"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2964953836.pdf","grobid_xml":"https://content.openalex.org/works/W2964953836.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W1973001156","https://openalex.org/W1987562803","https://openalex.org/W2011632873","https://openalex.org/W2019412213","https://openalex.org/W2022316530","https://openalex.org/W2096598900","https://openalex.org/W2097776316","https://openalex.org/W2100548092","https://openalex.org/W2115214414","https://openalex.org/W2121269638","https://openalex.org/W2150916025","https://openalex.org/W2157092487","https://openalex.org/W2161936973","https://openalex.org/W2166400748","https://openalex.org/W2167847032","https://openalex.org/W2585199909"],"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/W4386026606","https://openalex.org/W2897158376","https://openalex.org/W2807937018"],"abstract_inverted_index":{"We":[0],"study":[1],"the":[2,51],"problem":[3,22,45],"of":[4,14],"computing":[5],"similarity":[6,17,68],"joins":[7,18],"under":[8],"edit":[9],"distance":[10],"on":[11],"a":[12,20],"set":[13],"strings.":[15],"Edit":[16],"is":[19],"fundamental":[21],"in":[23,33,50],"databases,":[24],"data":[25,34],"mining":[26],"and":[27,36,66],"bioinformatics.":[28],"It":[29],"finds":[30],"important":[31],"applications":[32],"cleaning":[35],"integration,":[37],"collaborative":[38],"filtering,":[39],"genome":[40],"sequence":[41],"assembly,":[42],"etc.":[43],"This":[44],"has":[46],"attracted":[47],"significant":[48],"attention":[49],"past":[52],"two":[53],"decades.":[54],"However,":[55],"all":[56],"previous":[57],"algorithms":[58],"either":[59],"cannot":[60],"scale":[61],"well":[62],"to":[63],"long":[64],"strings":[65],"large":[67],"thresholds,":[69],"or":[70],"suffer":[71],"from":[72],"imperfect":[73],"accuracy.":[74]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2019-08-13T00:00:00"}