{"id":"https://openalex.org/W2060170830","doi":"https://doi.org/10.1145/2566486.2568017","title":"Efficient estimation for high similarities using odd sketches","display_name":"Efficient estimation for high similarities using odd sketches","publication_year":2014,"publication_date":"2014-04-07","ids":{"openalex":"https://openalex.org/W2060170830","doi":"https://doi.org/10.1145/2566486.2568017","mag":"2060170830"},"language":"en","primary_location":{"id":"doi:10.1145/2566486.2568017","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2566486.2568017","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd international conference on World wide web","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/A5062318856","display_name":"Michael Mitzenmacher","orcid":"https://orcid.org/0000-0001-5430-5457"},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Michael Mitzenmacher","raw_affiliation_strings":["Harvard University, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Harvard University, Cambridge, MA, USA","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014293815","display_name":"Rasmus Pagh","orcid":"https://orcid.org/0000-0002-1516-9306"},"institutions":[{"id":"https://openalex.org/I83467386","display_name":"IT University of Copenhagen","ror":"https://ror.org/02309jg23","country_code":"DK","type":"education","lineage":["https://openalex.org/I83467386"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Rasmus Pagh","raw_affiliation_strings":["IT University of Copenhagen, Copenhagen, Denmark","It university of copenhagen, copenhagen, denmark#TAB#"],"affiliations":[{"raw_affiliation_string":"IT University of Copenhagen, Copenhagen, Denmark","institution_ids":["https://openalex.org/I83467386"]},{"raw_affiliation_string":"It university of copenhagen, copenhagen, denmark#TAB#","institution_ids":["https://openalex.org/I83467386"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069747496","display_name":"Ninh Pham","orcid":"https://orcid.org/0000-0001-5768-9900"},"institutions":[{"id":"https://openalex.org/I83467386","display_name":"IT University of Copenhagen","ror":"https://ror.org/02309jg23","country_code":"DK","type":"education","lineage":["https://openalex.org/I83467386"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Ninh Pham","raw_affiliation_strings":["IT University of Copenhagen, Copenhagen, Denmark","It university of copenhagen, copenhagen, denmark#TAB#"],"affiliations":[{"raw_affiliation_string":"IT University of Copenhagen, Copenhagen, Denmark","institution_ids":["https://openalex.org/I83467386"]},{"raw_affiliation_string":"It university of copenhagen, copenhagen, denmark#TAB#","institution_ids":["https://openalex.org/I83467386"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5062318856"],"corresponding_institution_ids":["https://openalex.org/I2801851002"],"apc_list":null,"apc_paid":null,"fwci":3.4599,"has_fulltext":false,"cited_by_count":60,"citation_normalized_percentile":{"value":0.94240766,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"109","last_page":"118"},"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":0.9994000196456909,"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":0.9994000196456909,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9977999925613403,"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"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9969000220298767,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/jaccard-index","display_name":"Jaccard index","score":0.9551319479942322},{"id":"https://openalex.org/keywords/sketch","display_name":"Sketch","score":0.843537449836731},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.7168688774108887},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6625453233718872},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.6404953002929688},{"id":"https://openalex.org/keywords/locality-sensitive-hashing","display_name":"Locality-sensitive hashing","score":0.5439600348472595},{"id":"https://openalex.org/keywords/collaborative-filtering","display_name":"Collaborative filtering","score":0.5378957986831665},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.5153288245201111},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5145804286003113},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5112283229827881},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.34476935863494873},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3354343771934509},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3282513916492462},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.31385910511016846},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2928261160850525},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2783246338367462},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.21522817015647888},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.205307275056839},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.13590744137763977},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.09832718968391418}],"concepts":[{"id":"https://openalex.org/C203519979","wikidata":"https://www.wikidata.org/wiki/Q865360","display_name":"Jaccard index","level":3,"score":0.9551319479942322},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.843537449836731},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.7168688774108887},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6625453233718872},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6404953002929688},{"id":"https://openalex.org/C74270461","wikidata":"https://www.wikidata.org/wiki/Q1625299","display_name":"Locality-sensitive hashing","level":4,"score":0.5439600348472595},{"id":"https://openalex.org/C21569690","wikidata":"https://www.wikidata.org/wiki/Q94702","display_name":"Collaborative filtering","level":3,"score":0.5378957986831665},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.5153288245201111},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5145804286003113},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5112283229827881},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.34476935863494873},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3354343771934509},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3282513916492462},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.31385910511016846},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2928261160850525},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2783246338367462},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.21522817015647888},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.205307275056839},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.13590744137763977},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.09832718968391418},{"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/2566486.2568017","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2566486.2568017","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd international conference on World wide web","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.638.9855","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.638.9855","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.itu.dk/people/pagh/papers/oddsketch.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.718.7440","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.718.7440","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.itu.dk/people/ndap/OddSketch.pdf","raw_type":"text"},{"id":"pmh:oai:pure.atira.dk:publications/7235f03d-b8c2-4fed-8977-c0f1d2e574bc","is_oa":false,"landing_page_url":"http://dl.acm.org/citation.cfm?id=2568017","pdf_url":null,"source":{"id":"https://openalex.org/S4377196680","display_name":"IT University Of Copenhagen (IT University of Copenhagen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I83467386","host_organization_name":"IT University of Copenhagen","host_organization_lineage":["https://openalex.org/I83467386"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Mitzenmacher, M, Pagh, R & Pham, N D 2014, Efficient estimation for high similarities using odd sketches. in Proceedings of the 23rd international conference on World wide web : WWW '14. Association for Computing Machinery, pp. 109-118. https://doi.org/10.1145/2566486.2568017","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1200706951","display_name":null,"funder_award_id":"CCF-1320231, CNS-1228598, IIS-0964473, and CCF-0915922","funder_id":"https://openalex.org/F4320337389","funder_display_name":"Division of Information and Intelligent Systems"},{"id":"https://openalex.org/G4162865770","display_name":null,"funder_award_id":"CCF-1320231, CNS-1228598, IIS-0964473, and CCF-0915922","funder_id":"https://openalex.org/F4320337387","funder_display_name":"Division of Computing and Communication Foundations"},{"id":"https://openalex.org/G6480099505","display_name":null,"funder_award_id":"CCF-1320231, CNS-1228598, IIS-0964473, and CCF-0915922","funder_id":"https://openalex.org/F4320337388","funder_display_name":"Division of Computer and Network Systems"}],"funders":[{"id":"https://openalex.org/F4320320943","display_name":"Danmarks Grundforskningsfond","ror":"https://ror.org/00znyv691"},{"id":"https://openalex.org/F4320337387","display_name":"Division of Computing and Communication Foundations","ror":"https://ror.org/01mng8331"},{"id":"https://openalex.org/F4320337388","display_name":"Division of Computer and Network Systems","ror":"https://ror.org/02rdzmk74"},{"id":"https://openalex.org/F4320337389","display_name":"Division of Information and Intelligent Systems","ror":"https://ror.org/053a2cp42"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W107173025","https://openalex.org/W1595409123","https://openalex.org/W1785933978","https://openalex.org/W1983704604","https://openalex.org/W1984630650","https://openalex.org/W2029852131","https://openalex.org/W2048779798","https://openalex.org/W2053377618","https://openalex.org/W2061980234","https://openalex.org/W2081193615","https://openalex.org/W2085922539","https://openalex.org/W2102221597","https://openalex.org/W2113853816","https://openalex.org/W2123427850","https://openalex.org/W2126907894","https://openalex.org/W2132069633","https://openalex.org/W2140431670","https://openalex.org/W2145349611","https://openalex.org/W2152228468","https://openalex.org/W2152565070","https://openalex.org/W2320051939","https://openalex.org/W6604386673","https://openalex.org/W6637957267","https://openalex.org/W6674970736","https://openalex.org/W6679663036"],"related_works":["https://openalex.org/W2969477168","https://openalex.org/W3040424402","https://openalex.org/W2943824105","https://openalex.org/W2558988915","https://openalex.org/W3087567571","https://openalex.org/W2371326241","https://openalex.org/W2911483473","https://openalex.org/W4401133510","https://openalex.org/W2885569103","https://openalex.org/W2144265691"],"abstract_inverted_index":{"Estimating":[0],"set":[1],"similarity":[2,27],"is":[3,63],"a":[4,19,53,93],"central":[5],"problem":[6],"in":[7,65,121],"many":[8],"computer":[9],"applications.":[10],"In":[11],"this":[12,112],"paper":[13],"we":[14],"introduce":[15],"the":[16,25,37,40,44,97,103,116],"Odd":[17,50,106,119],"Sketch,":[18],"compact":[20],"binary":[21],"sketch":[22,38],"for":[23,57,87],"estimating":[24],"Jaccard":[26,83],"of":[28,33,39,43,59,96,99,105,118],"two":[29,34,45],"sets.":[30,46],"The":[31,78],"exclusive-or":[32],"sketches":[35],"equals":[36],"symmetric":[41],"difference":[42],"This":[47],"means":[48],"that":[49],"Sketches":[51,120],"provide":[52],"highly":[54],"space-efficient":[55],"estimator":[56],"sets":[58],"high":[60],"similarity,":[61,84],"which":[62],"relevant":[64,85],"applications":[66],"such":[67],"as":[68],"web":[69,133],"duplicate":[70,134],"detection,":[71],"collaborative":[72],"filtering,":[73],"and":[74,114,132],"association":[75,129],"rule":[76,130],"learning.":[77],"method":[79],"extends":[80],"to":[81,101],"weighted":[82],"e.g.":[86],"TF-IDF":[88],"vector":[89],"comparison.":[90],"We":[91],"present":[92],"theoretical":[94],"analysis":[95],"quality":[98],"estimation":[100],"guarantee":[102],"reliability":[104],"Sketch-based":[107],"estimators.":[108],"Our":[109],"experiments":[110],"confirm":[111],"efficiency,":[113],"demonstrate":[115],"efficiency":[117],"comparison":[122],"with":[123],"$b$-bit":[124],"minwise":[125],"hashing":[126],"schemes":[127],"on":[128],"learning":[131],"detection":[135],"tasks.":[136]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":4},{"year":2014,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}