{"id":"https://openalex.org/W4313291293","doi":"https://doi.org/10.1109/tkde.2022.3232689","title":"GoldFinger: Fast &amp; Approximate Jaccard for Efficient KNN Graph Constructions","display_name":"GoldFinger: Fast &amp; Approximate Jaccard for Efficient KNN Graph Constructions","publication_year":2022,"publication_date":"2022-12-29","ids":{"openalex":"https://openalex.org/W4313291293","doi":"https://doi.org/10.1109/tkde.2022.3232689"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2022.3232689","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2022.3232689","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":true,"oa_status":"green","oa_url":"https://inria.hal.science/hal-04394851v1/document","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049321288","display_name":"Rachid Guerraoui","orcid":"https://orcid.org/0000-0002-4794-8902"},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Rachid Guerraoui","raw_affiliation_strings":["EPFL, Lausanne, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EPFL, Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031849486","display_name":"Anne-Marie Kermarrec","orcid":"https://orcid.org/0000-0001-8187-724X"},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Anne-Marie Kermarrec","raw_affiliation_strings":["EPFL, Lausanne, Switzerland"],"raw_orcid":"https://orcid.org/0000-0001-8187-724X","affiliations":[{"raw_affiliation_string":"EPFL, Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023674470","display_name":"Guilhem Niot","orcid":"https://orcid.org/0000-0002-2497-8770"},"institutions":[{"id":"https://openalex.org/I113428412","display_name":"\u00c9cole Normale Sup\u00e9rieure de Lyon","ror":"https://ror.org/04zmssz18","country_code":"FR","type":"education","lineage":["https://openalex.org/I113428412","https://openalex.org/I203339264"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Guilhem Niot","raw_affiliation_strings":["ENS de Lyon, Lyon, France"],"raw_orcid":"https://orcid.org/0000-0002-2497-8770","affiliations":[{"raw_affiliation_string":"ENS de Lyon, Lyon, France","institution_ids":["https://openalex.org/I113428412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015367586","display_name":"Olivier Ruas","orcid":"https://orcid.org/0000-0002-6862-9046"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Olivier Ruas","raw_affiliation_strings":["Pathway, Paris, France"],"raw_orcid":"https://orcid.org/0000-0002-6862-9046","affiliations":[{"raw_affiliation_string":"Pathway, Paris, France","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061628886","display_name":"Fran\u00e7ois Ta\u0131\u0308ani","orcid":"https://orcid.org/0000-0002-9692-5678"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I2802519937","display_name":"Institut de Recherche en Informatique et Syst\u00e8mes Al\u00e9atoires","ror":"https://ror.org/00myn0z94","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I205703379","https://openalex.org/I2802204017","https://openalex.org/I2802519937","https://openalex.org/I28221208","https://openalex.org/I4210127572","https://openalex.org/I4210159245","https://openalex.org/I56067802"]},{"id":"https://openalex.org/I56067802","display_name":"Universit\u00e9 de Rennes","ror":"https://ror.org/015m7wh34","country_code":"FR","type":"education","lineage":["https://openalex.org/I56067802"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Fran\u00e7ois Ta\u00efani","raw_affiliation_strings":["Inria, CNRS, IRISA, University of Rennes, Rennes, France"],"raw_orcid":"https://orcid.org/0000-0002-9692-5678","affiliations":[{"raw_affiliation_string":"Inria, CNRS, IRISA, University of Rennes, Rennes, France","institution_ids":["https://openalex.org/I56067802","https://openalex.org/I2802519937","https://openalex.org/I1294671590"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5049321288"],"corresponding_institution_ids":["https://openalex.org/I5124864"],"apc_list":null,"apc_paid":null,"fwci":0.4166,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.696361,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"35","issue":"11","first_page":"11461","last_page":"11475"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9995999932289124,"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/T10237","display_name":"Cryptography and Data Security","score":0.9952999949455261,"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":0.8106740713119507},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6464340686798096},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4998493194580078},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4960385262966156},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4959288537502289},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.4146592617034912},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22814828157424927},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22011825442314148},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.18355447053909302}],"concepts":[{"id":"https://openalex.org/C203519979","wikidata":"https://www.wikidata.org/wiki/Q865360","display_name":"Jaccard index","level":3,"score":0.8106740713119507},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6464340686798096},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4998493194580078},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4960385262966156},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4959288537502289},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.4146592617034912},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22814828157424927},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22011825442314148},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.18355447053909302},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tkde.2022.3232689","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2022.3232689","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"},{"id":"pmh:oai:HAL:hal-04394851v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-04394851","pdf_url":"https://inria.hal.science/hal-04394851v1/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering, 2023, 35 (11), pp.11461-11475. &#x27E8;10.1109/TKDE.2022.3232689&#x27E9;","raw_type":"Journal articles"},{"id":"pmh:oai:infoscience.epfl.ch:308013","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/308013","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"WoS","raw_type":"research article"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-04394851v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-04394851","pdf_url":"https://inria.hal.science/hal-04394851v1/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering, 2023, 35 (11), pp.11461-11475. &#x27E8;10.1109/TKDE.2022.3232689&#x27E9;","raw_type":"Journal articles"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5234768326","display_name":null,"funder_award_id":"ANR-16-CE23-0016","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4313291293.pdf","grobid_xml":"https://content.openalex.org/works/W4313291293.grobid-xml"},"referenced_works_count":63,"referenced_works":["https://openalex.org/W145388748","https://openalex.org/W1914310517","https://openalex.org/W1968018561","https://openalex.org/W1992371516","https://openalex.org/W2012833704","https://openalex.org/W2016362819","https://openalex.org/W2022704179","https://openalex.org/W2026844232","https://openalex.org/W2031513076","https://openalex.org/W2040877664","https://openalex.org/W2054560962","https://openalex.org/W2055839530","https://openalex.org/W2060170830","https://openalex.org/W2065014987","https://openalex.org/W2080234606","https://openalex.org/W2097865464","https://openalex.org/W2106309168","https://openalex.org/W2109426455","https://openalex.org/W2110026675","https://openalex.org/W2110953678","https://openalex.org/W2117154949","https://openalex.org/W2130502756","https://openalex.org/W2132069633","https://openalex.org/W2133296809","https://openalex.org/W2136891251","https://openalex.org/W2147717514","https://openalex.org/W2155106456","https://openalex.org/W2159094788","https://openalex.org/W2161676522","https://openalex.org/W2170605888","https://openalex.org/W2188225224","https://openalex.org/W2219888463","https://openalex.org/W2228830251","https://openalex.org/W2411707397","https://openalex.org/W2497173630","https://openalex.org/W2808282156","https://openalex.org/W2885727077","https://openalex.org/W2890960987","https://openalex.org/W2934727176","https://openalex.org/W2945486614","https://openalex.org/W2949985202","https://openalex.org/W2952271919","https://openalex.org/W2955430211","https://openalex.org/W2962733107","https://openalex.org/W2962771342","https://openalex.org/W2963469388","https://openalex.org/W2963886823","https://openalex.org/W2964158883","https://openalex.org/W3012786227","https://openalex.org/W3103567827","https://openalex.org/W3173675318","https://openalex.org/W4249843299","https://openalex.org/W4253848051","https://openalex.org/W4288299803","https://openalex.org/W4300492315","https://openalex.org/W4400191782","https://openalex.org/W6638025820","https://openalex.org/W6648560114","https://openalex.org/W6677328822","https://openalex.org/W6679446029","https://openalex.org/W6679663036","https://openalex.org/W6684723771","https://openalex.org/W6754813029"],"related_works":["https://openalex.org/W4254879869","https://openalex.org/W3022576529","https://openalex.org/W2628526247","https://openalex.org/W2596401011","https://openalex.org/W2913569734","https://openalex.org/W3127229356","https://openalex.org/W2000801317","https://openalex.org/W2294604808","https://openalex.org/W2702570413","https://openalex.org/W2011017119"],"abstract_inverted_index":{"We":[0,17,118],"propose":[1],"<i>GoldFinger</i>":[2],",":[3],"a":[4,41,54,108],"new":[5],"<i>compact</i>":[6],"and":[7,34,76,133],"<i>fast-to-compute</i>":[8],"binary":[9],"representation":[10,63],"of":[11,21,29,44,64,82,115,136,144],"datasets":[12,89],"to":[13,50,99,102,110,126,138,149],"approximate":[14],"Jaccard's":[15],"index.":[16],"illustrate":[18],"the":[19,24,61,65,83,145],"effectiveness":[20],"GoldFinger":[22,37,122],"on":[23,86],"emblematic":[25],"big":[26],"data":[27,66,104],"problem":[28],"K-Nearest-Neighbor":[30],"(KNN)":[31],"graph":[32],"construction":[33],"show":[35,59,120],"that":[36,60,91,121],"can":[38,123],"drastically":[39],"accelerate":[40],"large":[42],"range":[43],"existing":[45],"KNN":[46,116,127],"algorithms":[47],"with":[48],"little":[49],"no":[51],"overhead.":[52],"As":[53],"side":[55],"effect,":[56],"we":[57],"also":[58,119],"compact":[62],"protects":[67],"users\u2019":[68],"privacy":[69],"<i>for":[70],"free</i>":[71],"by":[72,97],"providing":[73],"<i>k</i>":[74],"-anonymity":[75],"<i>l</i>":[77],"-diversity.":[78],"Our":[79],"extensive":[80],"evaluation":[81],"resulting":[84],"approach":[85,93],"several":[87],"realistic":[88],"shows":[90],"our":[92],"reduces":[94],"computation":[95],"times":[96],"up":[98,137],"78.9%":[100],"compared":[101],"raw":[103],"while":[105],"only":[106],"incurring":[107],"negligible":[109],"moderate":[111],"loss":[112],"in":[113],"terms":[114],"quality.":[117],"be":[124],"applied":[125],"queries":[128],"(a":[129],"widely-used":[130],"search":[131],"technique)":[132],"delivers":[134],"speedups":[135],"<inline-formula><tex-math":[139],"notation=\"LaTeX\">$\\times":[140],"3.55$</tex-math></inline-formula>":[141],"over":[142],"one":[143],"most":[146],"efficient":[147],"approaches":[148],"this":[150],"problem.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-05-07T13:39:58.223016","created_date":"2023-01-06T00:00:00"}