{"id":"https://openalex.org/W3083028011","doi":"https://doi.org/10.1109/tkde.2020.3021067","title":"A Review for Weighted MinHash Algorithms","display_name":"A Review for Weighted MinHash Algorithms","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3083028011","doi":"https://doi.org/10.1109/tkde.2020.3021067","mag":"3083028011"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2020.3021067","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2020.3021067","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-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/A5101428333","display_name":"Wei Wu","orcid":"https://orcid.org/0000-0002-0975-4613"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Wei Wu","raw_affiliation_strings":["Discipline of Business Analytics, The University of Sydney Business School, Darlington, NSW, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Discipline of Business Analytics, The University of Sydney Business School, Darlington, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365239","display_name":"Bin Li","orcid":"https://orcid.org/0000-0002-9633-0033"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Li","raw_affiliation_strings":["Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai, China","[School of Computer Science, Fudan University, 12478 Shanghai, Shanghai China (e-mail: libin82cn@gmail.com)]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"[School of Computer Science, Fudan University, 12478 Shanghai, Shanghai China (e-mail: libin82cn@gmail.com)]","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069988750","display_name":"Ling Chen","orcid":"https://orcid.org/0000-0002-6468-5729"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ling Chen","raw_affiliation_strings":["Centre for Artificial Intelligence, FEIT, University of Technology Sydney, Ultimo, NSW, Australia","[Centre for Artificial Intelligence, University of Technology, Sydney, Sydney, New South Wales Australia (e-mail: Ling.Chen@uts.edu.au)]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Artificial Intelligence, FEIT, University of Technology Sydney, Ultimo, NSW, Australia","institution_ids":["https://openalex.org/I114017466"]},{"raw_affiliation_string":"[Centre for Artificial Intelligence, University of Technology, Sydney, Sydney, New South Wales Australia (e-mail: Ling.Chen@uts.edu.au)]","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015817857","display_name":"Junbin Gao","orcid":"https://orcid.org/0000-0001-9803-0256"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Junbin Gao","raw_affiliation_strings":["Discipline of Business Analytics, The University of Sydney Business School, Darlington, NSW, Australia","[Discipline of Business Analytics, University of Sydney, Sydney, New South Wales Australia 2006 (e-mail: junbin.gao@sydney.edu.au)]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Discipline of Business Analytics, The University of Sydney Business School, Darlington, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]},{"raw_affiliation_string":"[Discipline of Business Analytics, University of Sydney, Sydney, New South Wales Australia 2006 (e-mail: junbin.gao@sydney.edu.au)]","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100438525","display_name":"Chengqi Zhang","orcid":"https://orcid.org/0000-0001-5715-7154"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Chengqi Zhang","raw_affiliation_strings":["Centre for Artificial Intelligence, FEIT, University of Technology Sydney, Ultimo, NSW, Australia","[Centre for Artificial Intelligence, University of Technology, Sydney, Sydney, New South Wales Australia (e-mail: Chengqi.Zhang@uts.edu.au)]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Artificial Intelligence, FEIT, University of Technology Sydney, Ultimo, NSW, Australia","institution_ids":["https://openalex.org/I114017466"]},{"raw_affiliation_string":"[Centre for Artificial Intelligence, University of Technology, Sydney, Sydney, New South Wales Australia (e-mail: Chengqi.Zhang@uts.edu.au)]","institution_ids":["https://openalex.org/I114017466"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2045,"currency":"USD","value_usd":2045},"apc_paid":null,"fwci":1.9997,"has_fulltext":false,"cited_by_count":43,"citation_normalized_percentile":{"value":0.87410926,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"1"},"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":0.9988999962806702,"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":0.9988999962806702,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9977999925613403,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9976999759674072,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/jaccard-index","display_name":"Jaccard index","score":0.8438060283660889},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7043238282203674},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5383554100990295},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.5046333074569702},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4905230402946472},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.35356706380844116},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3068549335002899},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.2578999400138855}],"concepts":[{"id":"https://openalex.org/C203519979","wikidata":"https://www.wikidata.org/wiki/Q865360","display_name":"Jaccard index","level":3,"score":0.8438060283660889},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7043238282203674},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5383554100990295},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.5046333074569702},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4905230402946472},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35356706380844116},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3068549335002899},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.2578999400138855},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tkde.2020.3021067","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2020.3021067","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W107173025","https://openalex.org/W1583707981","https://openalex.org/W1736726159","https://openalex.org/W1826419936","https://openalex.org/W1981053739","https://openalex.org/W1990366180","https://openalex.org/W1991800036","https://openalex.org/W1999092742","https://openalex.org/W2003108016","https://openalex.org/W2012833704","https://openalex.org/W2019336343","https://openalex.org/W2024988577","https://openalex.org/W2029852131","https://openalex.org/W2047756776","https://openalex.org/W2053377618","https://openalex.org/W2055289292","https://openalex.org/W2055906546","https://openalex.org/W2060170830","https://openalex.org/W2061980234","https://openalex.org/W2085922539","https://openalex.org/W2087487085","https://openalex.org/W2116867711","https://openalex.org/W2118410043","https://openalex.org/W2122056984","https://openalex.org/W2126907894","https://openalex.org/W2132069633","https://openalex.org/W2140431670","https://openalex.org/W2145349611","https://openalex.org/W2146266087","https://openalex.org/W2147717514","https://openalex.org/W2156855109","https://openalex.org/W2162006472","https://openalex.org/W2168467811","https://openalex.org/W2169557227","https://openalex.org/W2396991783","https://openalex.org/W2506582421","https://openalex.org/W2566913073","https://openalex.org/W2583214467","https://openalex.org/W2604248105","https://openalex.org/W2604710676","https://openalex.org/W2766353929","https://openalex.org/W2772632044","https://openalex.org/W2773990282","https://openalex.org/W2785764160","https://openalex.org/W2796341401","https://openalex.org/W2808673780","https://openalex.org/W2951006102","https://openalex.org/W2963517218","https://openalex.org/W2963895930","https://openalex.org/W2964071678","https://openalex.org/W3101111960","https://openalex.org/W3102219154","https://openalex.org/W6604386673","https://openalex.org/W6607776381","https://openalex.org/W6629956336","https://openalex.org/W6634599061","https://openalex.org/W6635113438","https://openalex.org/W6674970736","https://openalex.org/W6678016754","https://openalex.org/W6681272064","https://openalex.org/W6682042839","https://openalex.org/W6730356566","https://openalex.org/W6732287843","https://openalex.org/W6735619271","https://openalex.org/W6736598905","https://openalex.org/W6767612672"],"related_works":["https://openalex.org/W1994775821","https://openalex.org/W2012019886","https://openalex.org/W2091133150","https://openalex.org/W2945869148","https://openalex.org/W2398781203","https://openalex.org/W2009279505","https://openalex.org/W4206503171","https://openalex.org/W4366711670","https://openalex.org/W2972216353","https://openalex.org/W3203997580"],"abstract_inverted_index":{"Data":[0],"similarity":[1,17,32,60,80,95,189],"(or":[2],"distance)":[3],"computation":[4,33],"is":[5,71,88],"a":[6,72,159,174],"fundamental":[7],"research":[8],"topic":[9],"which":[10],"underpins":[11],"many":[12],"high-level":[13],"applications":[14],"based":[15],"on":[16,102],"measures":[18],"in":[19,26,62,168,187],"machine":[20],"learning":[21],"and":[22,43,67,84,104,129,131,135,165,182,192],"data":[23],"mining.":[24],"However,":[25],"large-scale":[27],"real-world":[28],"scenarios,":[29],"the":[30,51,78,92,106,119,133,139,144,150,163,178,183,188,193],"exact":[31],"has":[34],"become":[35],"daunting":[36],"due":[37],"to":[38,57,90,149],"\u201c3V\u201d":[39],"nature":[40],"(volume,":[41],"velocity":[42],"variety)":[44],"of":[45,64,81,96,109,138,177],"big":[46],"data.":[47],"In":[48,113],"this":[49,114],"case,":[50],"hashing":[52],"techniques":[53],"have":[54,157],"been":[55],"verified":[56],"efficiently":[58,76],"conduct":[59,173],"estimation":[61,190],"terms":[63],"both":[65],"theory":[66],"practice.":[68],"Currently,":[69],"MinHash":[70,87,111,121,141,147,153,180,185],"popular":[73],"technique":[74],"for":[75,162],"estimating":[77],"Jaccard":[79,94],"binary":[82],"sets":[83],"furthermore,":[85],"weighted":[86,97,110,120,140,146,152,184],"generalized":[89,93],"estimate":[91],"sets.":[98],"This":[99],"review":[100],"focuses":[101],"categorizing":[103],"discussing":[105],"existing":[107],"works":[108],"algorithms.":[112],"review,":[115],"we":[116,156],"mainly":[117],"categorize":[118],"algorithms":[122],"into":[123],"quantization-based":[124],"approaches,":[125],"\u201cactive":[126],"index\u201d-based":[127],"ones":[128,148,186],"others,":[130],"show":[132],"evolution":[134],"inherent":[136],"connection":[137],"algorithms,":[142,164],"from":[143],"integer":[145],"real-valued":[151],"ones.":[154],"Also,":[155],"developed":[158],"Python":[160],"toolbox":[161],"released":[166],"it":[167],"our":[169],"github.":[170],"We":[171],"experimentally":[172],"comprehensive":[175],"study":[176],"standard":[179],"algorithm":[181],"error":[191],"information":[194],"retrieval":[195],"task.":[196]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}