{"id":"https://openalex.org/W2126887541","doi":null,"title":"b-bit minwise hashing for estimating three-way similarities","display_name":"b-bit minwise hashing for estimating three-way similarities","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W2126887541","mag":"2126887541"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.231.2578","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.231.2578","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://books.nips.cc/papers/files/nips23/NIPS2010_1143.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5100435527","display_name":"Ping Li","orcid":"https://orcid.org/0000-0002-8515-7773","observed_orcids":["https://orcid.org/0000-0002-8515-7773","https://orcid.org/0000-0002-5979-8868","https://orcid.org/0000-0002-7985-8477","https://orcid.org/0000-0002-1503-0240","https://orcid.org/0000-0002-8391-6510","https://orcid.org/0000-0001-8285-8921","https://orcid.org/0000-0003-4725-4553"]},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ping Li","raw_affiliation_strings":["Department of Statistical Science, Cornell University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistical Science, Cornell University","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034735876","display_name":"Arnd Christian K\u00f6nig","orcid":"https://orcid.org/0009-0003-2460-5776","observed_orcids":["https://orcid.org/0009-0003-2460-5776"]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arnd Christian K\u00f6nig","raw_affiliation_strings":["Microsoft Research, Microsoft Corp"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Microsoft Corp","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":null,"display_name":"Wenhao Gui","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wenhao Gui","raw_affiliation_strings":["Department of Statistical Science, Cornell University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistical Science, Cornell University","institution_ids":["https://openalex.org/I205783295"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.1193,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.93953488,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":87,"max":98},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9624000191688538,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9624000191688538,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.01140000019222498,"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/T11719","display_name":"Data Quality and Management","score":0.006899999920278788,"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/jaccard-similarity","display_name":"Jaccard similarity","score":0.9850000143051147},{"id":"https://openalex.org/keywords/data-sparsity","display_name":"data sparsity","score":0.5059999823570251},{"id":"https://openalex.org/keywords/storage-reduction","display_name":"storage reduction","score":0.6169999837875366}],"concepts":[{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.7280428409576416},{"id":"https://openalex.org/C203519979","wikidata":"https://www.wikidata.org/wiki/Q865360","display_name":"Jaccard index","level":3,"score":0.690853476524353},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6764652729034424},{"id":"https://openalex.org/C187062812","wikidata":"https://www.wikidata.org/wiki/Q6322840","display_name":"K-independent hashing","level":5,"score":0.6691207885742188},{"id":"https://openalex.org/C122907437","wikidata":"https://www.wikidata.org/wiki/Q5318999","display_name":"Dynamic perfect hashing","level":5,"score":0.6243487596511841},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.6113853454589844},{"id":"https://openalex.org/C116058348","wikidata":"https://www.wikidata.org/wiki/Q846912","display_name":"Universal hashing","level":5,"score":0.6058229207992554},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.5593894720077515},{"id":"https://openalex.org/C36375716","wikidata":"https://www.wikidata.org/wiki/Q6553456","display_name":"Linear hashing","level":5,"score":0.5590039491653442},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5366325974464417},{"id":"https://openalex.org/C56856351","wikidata":"https://www.wikidata.org/wiki/Q1757218","display_name":"Consistent hashing","level":5,"score":0.5337565541267395},{"id":"https://openalex.org/C74270461","wikidata":"https://www.wikidata.org/wiki/Q1625299","display_name":"Locality-sensitive hashing","level":4,"score":0.45251205563545227},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.45104336738586426},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.45026639103889465},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4420253336429596},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.3950152099132538},{"id":"https://openalex.org/C138111711","wikidata":"https://www.wikidata.org/wiki/Q478351","display_name":"Double hashing","level":4,"score":0.2834417223930359},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2819204330444336},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.16068291664123535},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.157723069190979},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13011249899864197},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.231.2578","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.231.2578","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://books.nips.cc/papers/files/nips23/NIPS2010_1143.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W84889933","https://openalex.org/W118408326","https://openalex.org/W1480714498","https://openalex.org/W1482260876","https://openalex.org/W1569403765","https://openalex.org/W1574901103","https://openalex.org/W1593045043","https://openalex.org/W1963524312","https://openalex.org/W1975292433","https://openalex.org/W1978024959","https://openalex.org/W1983704604","https://openalex.org/W1986482242","https://openalex.org/W1991271936","https://openalex.org/W2001306626","https://openalex.org/W2012833704","https://openalex.org/W2029852131","https://openalex.org/W2031252661","https://openalex.org/W2040886165","https://openalex.org/W2044074944","https://openalex.org/W2047756776","https://openalex.org/W2048779798","https://openalex.org/W2049898997","https://openalex.org/W2053377618","https://openalex.org/W2112036337","https://openalex.org/W2121516976","https://openalex.org/W2126326837","https://openalex.org/W2127675794","https://openalex.org/W2129598390","https://openalex.org/W2130484710","https://openalex.org/W2132069633","https://openalex.org/W2140431670","https://openalex.org/W2142256417","https://openalex.org/W2145349611","https://openalex.org/W2147033904","https://openalex.org/W2147717514","https://openalex.org/W2150690310","https://openalex.org/W2151310484","https://openalex.org/W2152228468","https://openalex.org/W2152565070","https://openalex.org/W2158579916","https://openalex.org/W2160306106","https://openalex.org/W2169557227","https://openalex.org/W2169844574"],"related_works":["https://openalex.org/W2407551165","https://openalex.org/W1658216815","https://openalex.org/W2100141119","https://openalex.org/W2151596444","https://openalex.org/W79052446","https://openalex.org/W3160998283","https://openalex.org/W2702570413","https://openalex.org/W6885166917","https://openalex.org/W2097865464","https://openalex.org/W2152540969"],"abstract_inverted_index":{"Computing":[0],"1":[1,117],"two-way":[2],"and":[3,74,77],"multi-way":[4],"set":[5],"similarities":[6],"is":[7,63,72],"a":[8,80,98,109],"fundamental":[9],"problem.":[10],"This":[11],"study":[12],"focuses":[13],"on":[14,60],"estimating":[15],"3-way":[16,54,115],"resemblance":[17],"(Jaccard":[18],"similarity)":[19],"using":[20,33],"b-bit":[21,36,92],"minwise":[22,26,37,93],"hashing.":[23],"While":[24],"traditional":[25],"hashing":[27,38,94],"methods":[28],"store":[29],"each":[30],"hashed":[31],"value":[32],"64":[34],"bits,":[35],"only":[39],"stores":[40],"the":[41,57,68,104,114],"lowest":[42],"b":[43,46],"bits":[44],"(where":[45],"\u2265":[47],"2":[48],"for":[49,85,108],"3-way).":[50],"The":[51],"extension":[52],"to":[53,100],"similarity":[55,62],"from":[56],"prior":[58],"work":[59],"2-way":[61],"technically":[64],"non-trivial.":[65],"We":[66],"develop":[67],"precise":[69],"estimator":[70,83,111],"which":[71],"accurate":[73],"very":[75],"complicated;":[76],"we":[78],"recommend":[79],"much":[81],"simplified":[82],"suitable":[84],"sparse":[86],"data.":[87],"Our":[88],"analysis":[89],"shows":[90],"that":[91],"can":[95],"normally":[96],"achieve":[97],"10":[99],"25-fold":[101],"improvement":[102],"in":[103],"storage":[105],"space":[106],"required":[107],"given":[110],"accuracy":[112],"of":[113],"resemblance.":[116]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":4}],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2016-06-24T00:00:00"}