{"id":"https://openalex.org/W3001692356","doi":"https://doi.org/10.1109/tkde.2020.2969423","title":"Streaming Algorithms for Estimating High Set Similarities in LogLog Space","display_name":"Streaming Algorithms for Estimating High Set Similarities in LogLog Space","publication_year":2020,"publication_date":"2020-01-24","ids":{"openalex":"https://openalex.org/W3001692356","doi":"https://doi.org/10.1109/tkde.2020.2969423","mag":"3001692356"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2020.2969423","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2020.2969423","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/A5056609151","display_name":"Yiyan Qi","orcid":"https://orcid.org/0000-0002-8078-5834"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yiyan Qi","raw_affiliation_strings":["MOE Key Laboratory for Intelligent Networks and Network Security, Xi'an Jiaotong University, Xi'an, Shaanxi, China","[MOE Key Laboratory for Intelligent Networks and Network Security, Xi'an Jiaotong University, Xi'an, Shaanxi, China]"],"affiliations":[{"raw_affiliation_string":"MOE Key Laboratory for Intelligent Networks and Network Security, Xi'an Jiaotong University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"[MOE Key Laboratory for Intelligent Networks and Network Security, Xi'an Jiaotong University, Xi'an, Shaanxi, China]","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022240408","display_name":"Pinghui Wang","orcid":"https://orcid.org/0000-0001-5779-6108"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pinghui Wang","raw_affiliation_strings":["MOE Key Laboratory for Intelligent Networks and Network Security, Xi'an Jiaotong University, Xi'an, Shaanxi, China","[MOE Key Laboratory for Intelligent Networks and Network Security, Xi'an Jiaotong University, Xi'an, Shaanxi, China]"],"affiliations":[{"raw_affiliation_string":"MOE Key Laboratory for Intelligent Networks and Network Security, Xi'an Jiaotong University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"[MOE Key Laboratory for Intelligent Networks and Network Security, Xi'an Jiaotong University, Xi'an, Shaanxi, China]","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100710889","display_name":"Yuanming Zhang","orcid":"https://orcid.org/0000-0002-5579-638X"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanming Zhang","raw_affiliation_strings":["MOE Key Laboratory for Intelligent Networks and Network Security, Xi'an Jiaotong University, Xi'an, Shaanxi, China","[MOE Key Laboratory for Intelligent Networks and Network Security, Xi'an Jiaotong University, Xi'an, Shaanxi, China]"],"affiliations":[{"raw_affiliation_string":"MOE Key Laboratory for Intelligent Networks and Network Security, Xi'an Jiaotong University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"[MOE Key Laboratory for Intelligent Networks and Network Security, Xi'an Jiaotong University, Xi'an, Shaanxi, China]","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032033256","display_name":"Qiaozhu Zhai","orcid":"https://orcid.org/0000-0002-7312-4923"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiaozhu Zhai","raw_affiliation_strings":["MOE Key Laboratory for Intelligent Networks and Network Security, Xi'an Jiaotong University, Xi'an, Shaanxi, China","[MOE Key Laboratory for Intelligent Networks and Network Security, Xi'an Jiaotong University, Xi'an, Shaanxi, China]"],"affiliations":[{"raw_affiliation_string":"MOE Key Laboratory for Intelligent Networks and Network Security, Xi'an Jiaotong University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"[MOE Key Laboratory for Intelligent Networks and Network Security, Xi'an Jiaotong University, Xi'an, Shaanxi, China]","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100455048","display_name":"Chenxu Wang","orcid":"https://orcid.org/0000-0002-9539-5046"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenxu Wang","raw_affiliation_strings":["MOE Key Laboratory for Intelligent Networks and Network Security, Xi'an Jiaotong University, Xi'an, Shaanxi, China","[MOE Key Laboratory for Intelligent Networks and Network Security, Xi'an Jiaotong University, Xi'an, Shaanxi, China]"],"affiliations":[{"raw_affiliation_string":"MOE Key Laboratory for Intelligent Networks and Network Security, Xi'an Jiaotong University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"[MOE Key Laboratory for Intelligent Networks and Network Security, Xi'an Jiaotong University, Xi'an, Shaanxi, China]","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088460924","display_name":"Guangjian Tian","orcid":"https://orcid.org/0009-0007-2499-7916"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangjian Tian","raw_affiliation_strings":["Shenzhen Research Institute, Xi'an Jiaotong University, Shenzhen, China","Shenzhen Research Institute, Xi\u2019an Jiaotong University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Research Institute, Xi'an Jiaotong University, Shenzhen, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"Shenzhen Research Institute, Xi\u2019an Jiaotong University, Shenzhen, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068489266","display_name":"John C. S. Lui","orcid":"https://orcid.org/0000-0001-7466-0384"},"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":"John C.S. Lui","raw_affiliation_strings":["Tsinghua National Lab for Information Science and Technology, Center for Intelligent and Networked Systems, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua National Lab for Information Science and Technology, Center for Intelligent and Networked Systems, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075845093","display_name":"Xiaohong Guan","orcid":"https://orcid.org/0000-0002-8826-0362"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaohong Guan","raw_affiliation_strings":["Shenzhen Research Institute, Xi'an Jiaotong University, Shenzhen, China","Shenzhen Research Institute, Xi\u2019an Jiaotong University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Research Institute, Xi'an Jiaotong University, Shenzhen, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"Shenzhen Research Institute, Xi\u2019an Jiaotong University, Shenzhen, China","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5056609151"],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":0.9131,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.72948189,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"33","issue":"10","first_page":"3438","last_page":"3452"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9986000061035156,"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"}},"topics":[{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9986000061035156,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9983999729156494,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9976000189781189,"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":0.940590500831604},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7803345918655396},{"id":"https://openalex.org/keywords/sketch","display_name":"Sketch","score":0.7613831162452698},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5586679577827454},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5543938875198364},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4925404489040375},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3655150532722473},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32457464933395386},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23863458633422852},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.1456041932106018}],"concepts":[{"id":"https://openalex.org/C203519979","wikidata":"https://www.wikidata.org/wiki/Q865360","display_name":"Jaccard index","level":3,"score":0.940590500831604},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7803345918655396},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.7613831162452698},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5586679577827454},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5543938875198364},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4925404489040375},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3655150532722473},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32457464933395386},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23863458633422852},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.1456041932106018},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tkde.2020.2969423","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2020.2969423","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":[{"id":"https://openalex.org/G1067324075","display_name":null,"funder_award_id":"U1736205","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2126049948","display_name":null,"funder_award_id":"61902305","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4796592722","display_name":null,"funder_award_id":"61922067","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":79,"referenced_works":["https://openalex.org/W107173025","https://openalex.org/W120301130","https://openalex.org/W213282541","https://openalex.org/W1502916507","https://openalex.org/W1506430804","https://openalex.org/W1583707981","https://openalex.org/W1595409123","https://openalex.org/W1999092742","https://openalex.org/W2001474264","https://openalex.org/W2005731313","https://openalex.org/W2008365755","https://openalex.org/W2012833704","https://openalex.org/W2025051251","https://openalex.org/W2029852131","https://openalex.org/W2037046020","https://openalex.org/W2048346983","https://openalex.org/W2048779798","https://openalex.org/W2053377618","https://openalex.org/W2060170830","https://openalex.org/W2064379477","https://openalex.org/W2080745194","https://openalex.org/W2081193615","https://openalex.org/W2085901659","https://openalex.org/W2093270024","https://openalex.org/W2099480861","https://openalex.org/W2102221597","https://openalex.org/W2120031510","https://openalex.org/W2123845384","https://openalex.org/W2126907894","https://openalex.org/W2132069633","https://openalex.org/W2140431670","https://openalex.org/W2144982963","https://openalex.org/W2147017814","https://openalex.org/W2147717514","https://openalex.org/W2152228468","https://openalex.org/W2156855109","https://openalex.org/W2162006472","https://openalex.org/W2164776546","https://openalex.org/W2171013708","https://openalex.org/W2331307653","https://openalex.org/W2418258478","https://openalex.org/W2555576367","https://openalex.org/W2583214467","https://openalex.org/W2604101616","https://openalex.org/W2604248105","https://openalex.org/W2762566515","https://openalex.org/W2765866471","https://openalex.org/W2772632044","https://openalex.org/W2785764160","https://openalex.org/W2797817276","https://openalex.org/W2899702797","https://openalex.org/W2904953191","https://openalex.org/W2944916577","https://openalex.org/W2953358718","https://openalex.org/W2955464083","https://openalex.org/W2963436558","https://openalex.org/W2963924281","https://openalex.org/W2966567703","https://openalex.org/W2976908892","https://openalex.org/W3106272338","https://openalex.org/W3122471300","https://openalex.org/W4230940751","https://openalex.org/W4237421257","https://openalex.org/W4241451373","https://openalex.org/W4361959454","https://openalex.org/W6604386673","https://openalex.org/W6604797525","https://openalex.org/W6629956336","https://openalex.org/W6630411795","https://openalex.org/W6635113438","https://openalex.org/W6674970736","https://openalex.org/W6678016754","https://openalex.org/W6679663036","https://openalex.org/W6681658524","https://openalex.org/W6682042839","https://openalex.org/W6730356566","https://openalex.org/W6735619271","https://openalex.org/W6745439629","https://openalex.org/W6766310288"],"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/W2558988915","https://openalex.org/W2972216353"],"abstract_inverted_index":{"Estimating":[0],"set":[1],"similarity":[2,27],"and":[3,16,30,44,90,182,188],"detecting":[4],"highly":[5],"similar":[6],"sets":[7,29,72],"are":[8,81],"fundamental":[9],"problems":[10],"in":[11,83,116],"areas":[12],"such":[13],"as":[14,73,75],"databases":[15],"machine":[17],"learning.":[18],"MinHash":[19,43,66,89],"is":[20],"a":[21,84,106,138,150,170,178],"well-known":[22],"technique":[23],"for":[24,35,57,141,162],"approximating":[25],"Jaccard":[26,114],"of":[28,53,78,131,180,190],"has":[31],"been":[32],"successfully":[33],"used":[34],"many":[36],"applications.":[37],"Its":[38],"two":[39],"compressed":[40],"versions,":[41],"b-bit":[42,88],"Odd":[45,91],"Sketch,":[46],"can":[47,67],"significantly":[48],"reduce":[49],"the":[50,54,159,186],"memory":[51],"usage":[52],"MinHash,":[55,121],"especially":[56],"estimating":[58],"high":[59],"similarities":[60,62,115],"(i.e.,":[61],"around":[63],"1).":[64],"Although":[65],"be":[68],"applied":[69],"to":[70,94,111,136],"static":[71],"well":[74],"streaming":[76,85,97,117],"sets,":[77],"which":[79],"elements":[80],"given":[82],"fashion,":[86],"unfortunately,":[87],"Sketch":[92],"fail":[93],"deal":[95],"with":[96,120,155,169],"data.":[98],"To":[99],"solve":[100],"this":[101,145],"problem,":[102],"we":[103,147],"previously":[104],"designed":[105],"memory-efficient":[107],"sketch":[108,140],"method,":[109,152],"MaxLogHash,":[110,156],"accurately":[112],"estimate":[113],"sets.":[118],"Compared":[119,154],"our":[122,191],"method":[123],"uses":[124],"smaller":[125],"sized":[126],"registers":[127],"(each":[128],"register":[129],"consists":[130],"less":[132],"than":[133],"7":[134],"bits)":[135],"build":[137],"compact":[139],"each":[142,164],"set.":[143],"In":[144],"paper,":[146],"further":[148],"develop":[149],"faster":[151],"MaxLogOPH++.":[153],"MaxLogOPH++":[157],"reduces":[158],"time":[160],"complexity":[161],"updating":[163],"coming":[165],"element":[166],"from":[167],"O(k)":[168],"small":[171],"additional":[172],"memory.":[173],"We":[174],"conduct":[175],"experiments":[176],"on":[177],"variety":[179],"datasets,":[181],"experimental":[183],"results":[184],"demonstrate":[185],"efficiency":[187],"effectiveness":[189],"methods.":[192]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3}],"updated_date":"2026-03-08T08:50:53.379069","created_date":"2025-10-10T00:00:00"}