{"id":"https://openalex.org/W2037178322","doi":"https://doi.org/10.1109/bigdata.2014.7004210","title":"Representative subsets for big data learning using k-NN graphs","display_name":"Representative subsets for big data learning using k-NN graphs","publication_year":2014,"publication_date":"2014-10-01","ids":{"openalex":"https://openalex.org/W2037178322","doi":"https://doi.org/10.1109/bigdata.2014.7004210","mag":"2037178322"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2014.7004210","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2014.7004210","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055826525","display_name":"Raghvendra Mall","orcid":"https://orcid.org/0000-0003-1779-3150"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Raghvendra Mall","raw_affiliation_strings":["ESAT/STADIUS, KU Leuven, Belgium","KU Leuven, ESAT/STADIUS, Kasteelpark Arenberg 10, B-3001 Leuven, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ESAT/STADIUS, KU Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]},{"raw_affiliation_string":"KU Leuven, ESAT/STADIUS, Kasteelpark Arenberg 10, B-3001 Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005357018","display_name":"Vilen Jumutc","orcid":"https://orcid.org/0000-0003-4771-2411"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Vilen Jumutc","raw_affiliation_strings":["ESAT/STADIUS, KU Leuven, Belgium","KU Leuven, ESAT/STADIUS, Kasteelpark Arenberg 10, B-3001 Leuven, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ESAT/STADIUS, KU Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]},{"raw_affiliation_string":"KU Leuven, ESAT/STADIUS, Kasteelpark Arenberg 10, B-3001 Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022628045","display_name":"Rocco Langone","orcid":"https://orcid.org/0000-0002-7583-7003"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Rocco Langone","raw_affiliation_strings":["ESAT/STADIUS, KU Leuven, Belgium","KU Leuven, ESAT/STADIUS, Kasteelpark Arenberg 10, B-3001 Leuven, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ESAT/STADIUS, KU Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]},{"raw_affiliation_string":"KU Leuven, ESAT/STADIUS, Kasteelpark Arenberg 10, B-3001 Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078854904","display_name":"Johan A. K. Suykens","orcid":"https://orcid.org/0000-0002-8846-6352"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Johan A.K. Suykens","raw_affiliation_strings":["ESAT/STADIUS, KU Leuven, Belgium","KU Leuven, ESAT/STADIUS, Kasteelpark Arenberg 10, B-3001 Leuven, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ESAT/STADIUS, KU Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]},{"raw_affiliation_string":"KU Leuven, ESAT/STADIUS, Kasteelpark Arenberg 10, B-3001 Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.0552,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.91636241,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"37","last_page":"42"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.996399998664856,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9897000193595886,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.7389408349990845},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7086063623428345},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6072447299957275},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5978417992591858},{"id":"https://openalex.org/keywords/clustering-coefficient","display_name":"Clustering coefficient","score":0.539138674736023},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.496582567691803},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4728803038597107},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4289504289627075},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4076939821243286},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.36117154359817505}],"concepts":[{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.7389408349990845},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7086063623428345},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6072447299957275},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5978417992591858},{"id":"https://openalex.org/C22047676","wikidata":"https://www.wikidata.org/wiki/Q898680","display_name":"Clustering coefficient","level":3,"score":0.539138674736023},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.496582567691803},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4728803038597107},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4289504289627075},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4076939821243286},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.36117154359817505},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/bigdata.2014.7004210","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2014.7004210","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:lirias2repo.kuleuven.be:123456789/463480","is_oa":false,"landing_page_url":"https://lirias.kuleuven.be/bitstream/123456789/463480/2/14-118.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306401954","display_name":"Lirias (KU Leuven)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I99464096","host_organization_name":"KU Leuven","host_organization_lineage":["https://openalex.org/I99464096"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Big Data, Washington, USA, October 2014","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/12","score":0.5899999737739563,"display_name":"Responsible consumption and production"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W2946484","https://openalex.org/W79918814","https://openalex.org/W603723648","https://openalex.org/W1973412776","https://openalex.org/W1975594892","https://openalex.org/W1977788280","https://openalex.org/W1998378660","https://openalex.org/W2014296507","https://openalex.org/W2029685080","https://openalex.org/W2044842931","https://openalex.org/W2064340336","https://openalex.org/W2067563600","https://openalex.org/W2068019092","https://openalex.org/W2072596762","https://openalex.org/W2076346323","https://openalex.org/W2084812512","https://openalex.org/W2105681109","https://openalex.org/W2112545207","https://openalex.org/W2129905273","https://openalex.org/W2140565974","https://openalex.org/W2157462866","https://openalex.org/W2171074980","https://openalex.org/W2179342229","https://openalex.org/W2189465200","https://openalex.org/W2295917400","https://openalex.org/W2990650678","https://openalex.org/W3004511899","https://openalex.org/W3112020351","https://openalex.org/W3145128584","https://openalex.org/W3183881215","https://openalex.org/W4254917997","https://openalex.org/W6603230449","https://openalex.org/W6680922791","https://openalex.org/W6683124362","https://openalex.org/W6687322159"],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2935909890","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W1531601525","https://openalex.org/W17155033"],"abstract_inverted_index":{"In":[0],"this":[1,49,75],"paper":[2],"we":[3,46,56],"propose":[4,47],"a":[5,16,34,40,72],"deterministic":[6],"method":[7,66],"to":[8,69,108],"obtain":[9,71],"subsets":[10,118],"from":[11,85,120],"big":[12,76,105,144,148],"data":[13,77,106,145,149],"which":[14],"are":[15],"good":[17],"representative":[18,62],"of":[19,129],"the":[20,24,29,53,58,90,93,100,103,109,114,127,130],"inherent":[21],"structure":[22],"in":[23,48,89,102],"data.":[25],"We":[26,97,125],"first":[27],"convert":[28],"large":[30],"scale":[31],"dataset":[32],"into":[33],"sparse":[35],"undirected":[36],"k-NN":[37,54],"graph":[38,55,91],"using":[39],"distributed":[41],"network":[42],"generation":[43],"framework":[44],"that":[45],"paper.":[50],"After":[51],"obtaining":[52],"exploit":[57],"fast":[59],"and":[60,112,136,147],"unique":[61],"subset":[63,73,116,122,132],"(FURS)":[64],"selection":[65,81,123],"[1],":[67],"[2]":[68],"deterministically":[70],"for":[74,139],"network.":[78],"The":[79],"FURS":[80],"technique":[82],"selects":[83],"nodes":[84,111],"different":[86,140],"dense":[87],"regions":[88],"retaining":[92],"natural":[94],"community":[95],"structure.":[96],"then":[98],"locate":[99],"points":[101],"original":[104],"corresponding":[107],"selected":[110,131],"compare":[113],"obtained":[115],"with":[117],"acquired":[119],"state-of-the-art":[121],"techniques.":[124],"evaluate":[126],"quality":[128],"on":[133],"several":[134],"synthetic":[135],"real-life":[137],"datasets":[138],"learning":[141],"tasks":[142],"including":[143],"classification":[146],"clustering.":[150]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}