{"id":"https://openalex.org/W2952271919","doi":"https://doi.org/10.1109/icde.2019.00186","title":"Fingerprinting Big Data: The Case of KNN Graph Construction","display_name":"Fingerprinting Big Data: The Case of KNN Graph Construction","publication_year":2019,"publication_date":"2019-04-01","ids":{"openalex":"https://openalex.org/W2952271919","doi":"https://doi.org/10.1109/icde.2019.00186","mag":"2952271919"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2019.00186","pdf_url":null,"source":{"id":"https://openalex.org/S4363607857","display_name":"2022 IEEE 38th International Conference on Data Engineering (ICDE)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"preprint","type_crossref":"proceedings-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://inria.hal.science/hal-01904341/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":false,"raw_author_name":"Rachid Guerraoui","raw_affiliation_strings":["Distributed Programming Laboratory","Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne"],"affiliations":[{"raw_affiliation_string":"Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne","institution_ids":["https://openalex.org/I5124864"]},{"raw_affiliation_string":"Distributed Programming Laboratory","institution_ids":[]}]},{"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":["Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne","Mediego [Cesson-S\u00e9vign\u00e9]"],"affiliations":[{"raw_affiliation_string":"Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne","institution_ids":["https://openalex.org/I5124864"]},{"raw_affiliation_string":"Mediego [Cesson-S\u00e9vign\u00e9]","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015367586","display_name":"Olivier Ruas","orcid":"https://orcid.org/0000-0002-6862-9046"},"institutions":[{"id":"https://openalex.org/I4210133778","display_name":"Inria Rennes - Bretagne Atlantique Research Centre","ror":"https://ror.org/04040yw90","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210133778"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Olivier Ruas","raw_affiliation_strings":["Inria Rennes \u2013 Bretagne Atlantique","the World Is Distributed Exploring the tension between scale and coordination"],"affiliations":[{"raw_affiliation_string":"the World Is Distributed Exploring the tension between scale and coordination","institution_ids":[]},{"raw_affiliation_string":"Inria Rennes \u2013 Bretagne Atlantique","institution_ids":["https://openalex.org/I4210133778"]}]},{"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":[],"countries":[],"is_corresponding":false,"raw_author_name":"Francois Taiani","raw_affiliation_strings":["the World Is Distributed Exploring the tension between scale and coordination"],"affiliations":[{"raw_affiliation_string":"the World Is Distributed Exploring the tension between scale and coordination","institution_ids":[]}]}],"institution_assertions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":7,"citation_normalized_percentile":{"value":0.839626,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":82,"max":84},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Techniques for Data Analysis and Machine Learning","score":0.9961,"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 Techniques for Data Analysis and Machine Learning","score":0.9961,"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/T10388","display_name":"Digital Image Watermarking Techniques","score":0.9822,"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/data-hiding","display_name":"Data Hiding","score":0.554429},{"id":"https://openalex.org/keywords/image-authentication","display_name":"Image Authentication","score":0.527542},{"id":"https://openalex.org/keywords/information-embedding","display_name":"Information Embedding","score":0.522459},{"id":"https://openalex.org/keywords/federated-learning","display_name":"Federated Learning","score":0.520732},{"id":"https://openalex.org/keywords/robust-hashing","display_name":"Robust Hashing","score":0.518424}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8174677},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5949349},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5679214},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5236856},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4997213},{"id":"https://openalex.org/C113238511","wikidata":"https://www.wikidata.org/wiki/Q1071612","display_name":"k-nearest neighbors algorithm","level":2,"score":0.4994762},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.4799914},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.4354415},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.36871043},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29852974},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09743139},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":7,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2019.00186","pdf_url":null,"source":{"id":"https://openalex.org/S4363607857","display_name":"2022 IEEE 38th International Conference on Data Engineering (ICDE)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://hal.inria.fr/hal-01904341","pdf_url":"https://inria.hal.science/hal-01904341/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":true,"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":["Centre National de la Recherche Scientifique"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://hal.inria.fr/hal-02357950","pdf_url":"https://inria.hal.science/hal-02357950/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":true,"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":["Centre National de la Recherche Scientifique"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/267844","pdf_url":"https://infoscience.epfl.ch/record/267844/files/08731479.pdf","source":{"id":"https://openalex.org/S4306400488","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":true,"landing_page_url":"https://hal.inria.fr/hal-02357950/file/Fingerprinting%20Big%20Data%3A%20The%20Case%20of%20KNN%20Graph%20Construction.pdf","pdf_url":"https://hal.inria.fr/hal-02357950/file/Fingerprinting%20Big%20Data%3A%20The%20Case%20of%20KNN%20Graph%20Construction.pdf","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":true,"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":["Centre National de la Recherche Scientifique"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://hal.inria.fr/hal-02357950/document","pdf_url":"https://hal.inria.fr/hal-02357950/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":true,"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":["Centre National de la Recherche Scientifique"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://hal.inria.fr/hal-01904341/file/RR-9218.pdf","pdf_url":"https://hal.inria.fr/hal-01904341/file/RR-9218.pdf","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":true,"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":["Centre National de la Recherche Scientifique"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://hal.inria.fr/hal-01904341","pdf_url":"https://inria.hal.science/hal-01904341/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":true,"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":["Centre National de la Recherche Scientifique"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":29,"referenced_works":["https://openalex.org/W1562654179","https://openalex.org/W1566717980","https://openalex.org/W1770242755","https://openalex.org/W1968018561","https://openalex.org/W2016362819","https://openalex.org/W2026844232","https://openalex.org/W2031513076","https://openalex.org/W2054560962","https://openalex.org/W2097865464","https://openalex.org/W2106309168","https://openalex.org/W2110026675","https://openalex.org/W2130502756","https://openalex.org/W2132069633","https://openalex.org/W2133296809","https://openalex.org/W2136891251","https://openalex.org/W2138064700","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/W2885727077","https://openalex.org/W3005838368","https://openalex.org/W4236647746","https://openalex.org/W4253848051","https://openalex.org/W4300492315"],"related_works":["https://openalex.org/W4390608645","https://openalex.org/W4255224757","https://openalex.org/W4247566972","https://openalex.org/W4233347783","https://openalex.org/W4206777497","https://openalex.org/W3090563135","https://openalex.org/W2960264696","https://openalex.org/W2910064364","https://openalex.org/W2499527417","https://openalex.org/W2497432351"],"abstract_inverted_index":{"We":[0],"propose":[1],"fingerprinting,":[2],"a":[3,42,92],"new":[4],"technique":[5],"that":[6,37,73],"consists":[7],"in":[8,97],"constructing":[9],"compact,":[10],"fast-to-compute":[11],"and":[12,35],"privacypreserving":[13],"binary":[14],"representations":[15],"of":[16,21,30,45,62,78,86,99],"datasets.We":[17],"illustrate":[18],"the":[19,25,52,63,84],"effectiveness":[20],"our":[22,74],"approach":[23,65,75],"on":[24,68],"emblematic":[26],"big":[27],"data":[28,88],"problem":[29],"K-Nearest-Neighbor":[31],"(KNN)":[32],"graph":[33],"construction":[34],"show":[36],"fingerprinting":[38],"can":[39],"drastically":[40],"accelerate":[41],"large":[43],"range":[44],"existing":[46],"KNN":[47,100],"algorithms,":[48],"while":[49,89],"efficiently":[50],"obfuscating":[51],"original":[53],"data,":[54],"with":[55],"little":[56],"to":[57,80,83,94],"no":[58],"overhead.Our":[59],"extensive":[60],"evaluation":[61],"resulting":[64],"(dubbed":[66],"GoldFinger)":[67],"several":[69],"realistic":[70],"datasets":[71],"shows":[72],"delivers":[76],"speedups":[77],"up":[79],"78.9%":[81],"compared":[82],"use":[85],"raw":[87],"only":[90],"incurring":[91],"negligible":[93],"moderate":[95],"loss":[96],"terms":[98],"quality.":[101]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2952271919","counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3}],"updated_date":"2024-11-23T17:46:56.210389","created_date":"2019-06-27"}
