{"id":"https://openalex.org/W2031944888","doi":"https://doi.org/10.1109/bigdata.2014.7004276","title":"Building k-nn graphs from large text data","display_name":"Building k-nn graphs from large text data","publication_year":2014,"publication_date":"2014-10-01","ids":{"openalex":"https://openalex.org/W2031944888","doi":"https://doi.org/10.1109/bigdata.2014.7004276","mag":"2031944888"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2014.7004276","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2014.7004276","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-01133324","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050650048","display_name":"Thibault Debatty","orcid":"https://orcid.org/0000-0003-2373-566X"},"institutions":[{"id":"https://openalex.org/I150517870","display_name":"Royal Military Academy","ror":"https://ror.org/02vmnye06","country_code":"BE","type":"education","lineage":["https://openalex.org/I150517870"]},{"id":"https://openalex.org/I1902872","display_name":"EURECOM","ror":"https://ror.org/00sse7z02","country_code":"FR","type":"education","lineage":["https://openalex.org/I1902872","https://openalex.org/I205703379"]}],"countries":["BE","FR"],"is_corresponding":false,"raw_author_name":"Thibault Debatty","raw_affiliation_strings":["Royal Military Academy, Brussels, Belgium","Royal Military Academy (RMA) (Belgium)","Eurecom [Sophia Antipolis] (Campus SophiaTech, 450 Route des Chappes, CS 50193 - 06904 Biot Sophia Antipolis cedex - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Royal Military Academy, Brussels, Belgium","institution_ids":["https://openalex.org/I150517870"]},{"raw_affiliation_string":"Royal Military Academy (RMA) (Belgium)","institution_ids":["https://openalex.org/I150517870"]},{"raw_affiliation_string":"Eurecom [Sophia Antipolis] (Campus SophiaTech, 450 Route des Chappes, CS 50193 - 06904 Biot Sophia Antipolis cedex - France)","institution_ids":["https://openalex.org/I1902872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017009335","display_name":"Pietro Michiardi","orcid":"https://orcid.org/0000-0003-4675-7677"},"institutions":[{"id":"https://openalex.org/I1902872","display_name":"EURECOM","ror":"https://ror.org/00sse7z02","country_code":"FR","type":"education","lineage":["https://openalex.org/I1902872","https://openalex.org/I205703379"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Pietro Michiardi","raw_affiliation_strings":["EURECOM, Campus Sophia Tech, France","Eurecom [Sophia Antipolis] (Campus SophiaTech, 450 Route des Chappes, CS 50193 - 06904 Biot Sophia Antipolis cedex - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EURECOM, Campus Sophia Tech, France","institution_ids":["https://openalex.org/I1902872"]},{"raw_affiliation_string":"Eurecom [Sophia Antipolis] (Campus SophiaTech, 450 Route des Chappes, CS 50193 - 06904 Biot Sophia Antipolis cedex - France)","institution_ids":["https://openalex.org/I1902872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076214057","display_name":"Olivier Thonnard","orcid":"https://orcid.org/0000-0003-2390-0346"},"institutions":[{"id":"https://openalex.org/I4210098805","display_name":"NortonLifeLock (Ireland)","ror":"https://ror.org/0114r0003","country_code":"IE","type":"company","lineage":["https://openalex.org/I1308906816","https://openalex.org/I4210098805"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Olivier Thonnard","raw_affiliation_strings":["Symantec Research Labs, Sophia Antipolis, France","Symantec Research Labs (Ireland)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Symantec Research Labs, Sophia Antipolis, France","institution_ids":[]},{"raw_affiliation_string":"Symantec Research Labs (Ireland)","institution_ids":["https://openalex.org/I4210098805"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022101559","display_name":"Wim Mees","orcid":"https://orcid.org/0000-0002-0696-8093"},"institutions":[{"id":"https://openalex.org/I150517870","display_name":"Royal Military Academy","ror":"https://ror.org/02vmnye06","country_code":"BE","type":"education","lineage":["https://openalex.org/I150517870"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Wim Mees","raw_affiliation_strings":["Royalct Military Academy, Brussels, Belgium","Royal Military Academy (RMA) (Belgium)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Royalct Military Academy, Brussels, Belgium","institution_ids":["https://openalex.org/I150517870"]},{"raw_affiliation_string":"Royal Military Academy (RMA) (Belgium)","institution_ids":["https://openalex.org/I150517870"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7198,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.75213582,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"10","issue":null,"first_page":"573","last_page":"578"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11478","display_name":"Caching and Content Delivery","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.9976000189781189,"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/T11269","display_name":"Algorithms and Data Compression","score":0.996999979019165,"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/computer-science","display_name":"Computer science","score":0.786294162273407},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6163399815559387},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6015928387641907},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.5516704320907593},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5236746668815613},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.439238965511322},{"id":"https://openalex.org/keywords/piecewise","display_name":"Piecewise","score":0.43085020780563354},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3970022201538086},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3384475111961365},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3332832157611847},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.16095000505447388},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11495596170425415},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.09713637828826904}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.786294162273407},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6163399815559387},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6015928387641907},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.5516704320907593},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5236746668815613},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.439238965511322},{"id":"https://openalex.org/C164660894","wikidata":"https://www.wikidata.org/wiki/Q2037833","display_name":"Piecewise","level":2,"score":0.43085020780563354},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3970022201538086},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3384475111961365},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3332832157611847},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.16095000505447388},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11495596170425415},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.09713637828826904},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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":3,"locations":[{"id":"doi:10.1109/bigdata.2014.7004276","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2014.7004276","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-01133324v1","is_oa":true,"landing_page_url":"https://hal.science/hal-01133324","pdf_url":null,"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE International Conference on Big Data (Big Data), 2014, Oct 2014, Washington DC, United States. ⟨10.1109/BigData.2014.7004276⟩","raw_type":"Conference papers"},{"id":"pmh:oai:fr.eurecom:4462","is_oa":false,"landing_page_url":"http://www.eurecom.fr/publication/4462","pdf_url":null,"source":{"id":"https://openalex.org/S4377196942","display_name":"Graduate School and Research Center in Digital Science (EURECOM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1902872","host_organization_name":"EURECOM","host_organization_lineage":["https://openalex.org/I1902872"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BIGDATA 2014, IEEE International Conference on Big Data, 27-30 October 2014, Washington DC, USA","raw_type":"Conference"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-01133324v1","is_oa":true,"landing_page_url":"https://hal.science/hal-01133324","pdf_url":null,"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE International Conference on Big Data (Big Data), 2014, Oct 2014, Washington DC, United States. ⟨10.1109/BigData.2014.7004276⟩","raw_type":"Conference papers"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W41404523","https://openalex.org/W206566442","https://openalex.org/W2097308346","https://openalex.org/W2110026675","https://openalex.org/W2130502756","https://openalex.org/W2161854574","https://openalex.org/W2168018439","https://openalex.org/W6679446029","https://openalex.org/W6684624762"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2146343568","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2013643406","https://openalex.org/W2027972911","https://openalex.org/W2157978810","https://openalex.org/W3138386522","https://openalex.org/W2499279132"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3],"present":[4],"our":[5,105],"new":[6],"design":[7],"of":[8,29,55,58,66,70,76,86,102,123,133],"NNCTPH,":[9],"a":[10,26,44,96,99,138],"scalable":[11],"algorithm":[12,24,72,94,108],"to":[13,34,61,110,113],"build":[14],"an":[15],"approximate":[16],"k-NN":[17],"graph":[18],"from":[19],"large":[20,143],"text":[21,144],"datasets.":[22,145],"The":[23],"uses":[25,42],"modified":[27],"version":[28],"Context":[30],"Triggered":[31],"Piecewise":[32],"Hashing":[33],"bin":[35],"the":[36,56,64,67,71,74,84,87,93,107,120,127,131,134],"input":[37],"data":[38],"into":[39],"buckets,":[40],"and":[41,82,98],"NN-Descent,":[43,118],"versatile":[45],"graph-building":[46],"algorithm,":[47],"inside":[48],"each":[49],"bucket.":[50],"We":[51,90],"use":[52],"datasets":[53],"consisting":[54],"subject":[57],"spam":[59],"emails":[60],"experimentally":[62],"test":[63],"influence":[65],"different":[68],"parameters":[69],"on":[73,79,83],"number":[75],"computed":[77],"similarities,":[78],"processing":[80],"time,":[81],"quality":[85,122],"final":[88],"graph.":[89,125],"also":[91],"compare":[92],"with":[95,130],"sequential":[97],"MapReduce":[100],"implementation":[101],"NN-Descent.":[103],"For":[104],"datasets,":[106],"proved":[109],"be":[111],"up":[112],"ten":[114],"times":[115],"faster":[116],"than":[117],"for":[119,141],"same":[121],"produced":[124],"Moreover,":[126],"speedup":[128],"increased":[129],"size":[132],"dataset,":[135],"making":[136],"NNCTPH":[137],"sensible":[139],"choice":[140],"very":[142]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}