{"id":"https://openalex.org/W4306735095","doi":"https://doi.org/10.1007/s10618-022-00869-6","title":"Large scale K-means clustering using GPUs","display_name":"Large scale K-means clustering using GPUs","publication_year":2022,"publication_date":"2022-10-18","ids":{"openalex":"https://openalex.org/W4306735095","doi":"https://doi.org/10.1007/s10618-022-00869-6"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10618-022-00869-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10618-022-00869-6.pdf","source":{"id":"https://openalex.org/S121920818","display_name":"Data Mining and Knowledge Discovery","issn_l":"1384-5810","issn":["1384-5810","1573-756X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319965","https://openalex.org/P4310319900"],"host_organization_lineage_names":["Springer Nature","Springer Science+Business Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},"type":"article","type_crossref":"journal-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10618-022-00869-6.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007482249","display_name":"Mi Li","orcid":"https://orcid.org/0000-0001-7158-3395"},"institutions":[{"id":"https://openalex.org/I52179390","display_name":"University of Waikato","ror":"https://ror.org/013fsnh78","country_code":"NZ","type":"education","lineage":["https://openalex.org/I52179390"]}],"countries":["NZ"],"is_corresponding":true,"raw_author_name":"Mi Li","raw_affiliation_strings":["Department of Computer Science, University of Waikato, Hamilton, New Zealand"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Waikato, Hamilton, New Zealand","institution_ids":["https://openalex.org/I52179390"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059992863","display_name":"Eibe Frank","orcid":"https://orcid.org/0000-0001-6152-7111"},"institutions":[{"id":"https://openalex.org/I52179390","display_name":"University of Waikato","ror":"https://ror.org/013fsnh78","country_code":"NZ","type":"education","lineage":["https://openalex.org/I52179390"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Eibe Frank","raw_affiliation_strings":["Department of Computer Science, University of Waikato, Hamilton, New Zealand"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Waikato, Hamilton, New Zealand","institution_ids":["https://openalex.org/I52179390"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087785022","display_name":"Bernhard Pfahringer","orcid":"https://orcid.org/0000-0002-3732-5787"},"institutions":[{"id":"https://openalex.org/I52179390","display_name":"University of Waikato","ror":"https://ror.org/013fsnh78","country_code":"NZ","type":"education","lineage":["https://openalex.org/I52179390"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Bernhard Pfahringer","raw_affiliation_strings":["Department of Computer Science, University of Waikato, Hamilton, New Zealand"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Waikato, Hamilton, New Zealand","institution_ids":["https://openalex.org/I52179390"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5007482249"],"corresponding_institution_ids":["https://openalex.org/I52179390"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990,"provenance":"doaj"},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990,"provenance":"doaj"},"fwci":1.386,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.694314,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":90},"biblio":{"volume":"37","issue":"1","first_page":"67","last_page":"109"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Data Clustering Techniques and Algorithms","score":0.9995,"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/T10637","display_name":"Data Clustering Techniques and Algorithms","score":0.9995,"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/T12761","display_name":"Adaptation to Concept Drift in Data Streams","score":0.9981,"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/T10057","display_name":"Face Recognition and Dimensionality Reduction Techniques","score":0.9947,"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/k-means","display_name":"K-means","score":0.560765},{"id":"https://openalex.org/keywords/semi-supervised-clustering","display_name":"Semi-supervised Clustering","score":0.554672},{"id":"https://openalex.org/keywords/density-based-clustering","display_name":"Density-based Clustering","score":0.554005},{"id":"https://openalex.org/keywords/clustering-algorithms","display_name":"Clustering Algorithms","score":0.545327},{"id":"https://openalex.org/keywords/support-vector-machines","display_name":"Support Vector Machines","score":0.543568},{"id":"https://openalex.org/keywords/gpu-cluster","display_name":"GPU cluster","score":0.51089925}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8568818},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.69912964},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.61380726},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.54831475},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.5138095},{"id":"https://openalex.org/C2781335571","wikidata":"https://www.wikidata.org/wiki/Q2633544","display_name":"GPU cluster","level":3,"score":0.51089925},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.47933802},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.44167796},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.4196231},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.12821206},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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":2,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10618-022-00869-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10618-022-00869-6.pdf","source":{"id":"https://openalex.org/S121920818","display_name":"Data Mining and Knowledge Discovery","issn_l":"1384-5810","issn":["1384-5810","1573-756X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319965","https://openalex.org/P4310319900"],"host_organization_lineage_names":["Springer Nature","Springer Science+Business Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":true,"landing_page_url":"https://hdl.handle.net/10289/15285","pdf_url":"https://researchcommons.waikato.ac.nz/bitstream/10289/15285/2/s10618-022-00869-6.pdf","source":{"id":"https://openalex.org/S4306400944","display_name":"Research Commons (University of Waikato)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I52179390","host_organization_name":"University of Waikato","host_organization_lineage":["https://openalex.org/I52179390"],"host_organization_lineage_names":["University of Waikato"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10618-022-00869-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10618-022-00869-6.pdf","source":{"id":"https://openalex.org/S121920818","display_name":"Data Mining and Knowledge Discovery","issn_l":"1384-5810","issn":["1384-5810","1573-756X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319965","https://openalex.org/P4310319900"],"host_organization_lineage_names":["Springer Nature","Springer Science+Business Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[],"grants":[{"funder":"https://openalex.org/F4320311746","funder_display_name":"University of Waikato","award_id":null}],"datasets":[],"versions":[],"referenced_works_count":31,"referenced_works":["https://openalex.org/W118481696","https://openalex.org/W1501500081","https://openalex.org/W1530232144","https://openalex.org/W1597797845","https://openalex.org/W171957664","https://openalex.org/W180242331","https://openalex.org/W1864199185","https://openalex.org/W1947439047","https://openalex.org/W1999756918","https://openalex.org/W2011430131","https://openalex.org/W2019334886","https://openalex.org/W2036477303","https://openalex.org/W2050408568","https://openalex.org/W2057923756","https://openalex.org/W2063257142","https://openalex.org/W2066815973","https://openalex.org/W2070630412","https://openalex.org/W2108399535","https://openalex.org/W2121910516","https://openalex.org/W2128022558","https://openalex.org/W2150593711","https://openalex.org/W2153233077","https://openalex.org/W2166771168","https://openalex.org/W2268856018","https://openalex.org/W2891639990","https://openalex.org/W3015604234","https://openalex.org/W3048170716","https://openalex.org/W3174479087","https://openalex.org/W3202378034","https://openalex.org/W4250981202","https://openalex.org/W79970639"],"related_works":["https://openalex.org/W4297775710","https://openalex.org/W2888918673","https://openalex.org/W2161462353","https://openalex.org/W2104603305","https://openalex.org/W2082176405","https://openalex.org/W2071296827","https://openalex.org/W2056717482","https://openalex.org/W2030707850","https://openalex.org/W2017587301","https://openalex.org/W1937514268"],"abstract_inverted_index":{"Abstract":[0],"The":[1,89],"k":[2,25,38,103,167,207,215],"-means":[3,31,39,104,168,193,216],"algorithm":[4,22,61,78,90,148,156,177],"is":[5,178],"widely":[6],"used":[7,229],"for":[8,23,50],"clustering,":[9,51],"compressing,":[10],"and":[11,19,96,140,145,209],"summarizing":[12],"vector":[13],"data.":[14],"We":[15],"present":[16],"a":[17,93,108,162,202],"fast":[18],"memory-efficient":[20],"GPU-based":[21,37,163,204,214],"exact":[24],"-means,":[26,208],"Asynchronous":[27],"Selective":[28],"Batched":[29],"K":[30,33,192],"(ASB":[32],"-means).":[34],"Unlike":[35],"most":[36],"algorithms":[40],"that":[41,131,190],"require":[42],"loading":[43],"the":[44,48,52,70,73,85,98,116,126,137,141,147,175,181,213,227],"whole":[45,74,182],"dataset":[46,183],"onto":[47],"GPU":[49,55,87,186],"amount":[53],"of":[54,72,128,165,174,206],"memory":[56,144],"required":[57],"to":[58,65,106,133,149,197],"run":[59,195],"our":[60,77,231],"can":[62,79,157,194],"be":[63,66,134,158],"chosen":[64],"much":[67],"smaller":[68],"than":[69,161,201],"size":[71,83],"dataset.":[75],"Thus,":[76],"cluster":[80,117],"datasets":[81,228],"whose":[82],"exceeds":[84],"available":[86],"memory.":[88,187],"works":[91],"in":[92,101,170,218,230],"batched":[94],"fashion":[95],"applies":[97],"triangle":[99],"inequality":[100],"each":[102],"iteration":[105],"omit":[107],"data":[109,129],"point":[110],"if":[111],"its":[112],"membership":[113],"assignment,":[114],"i.e.,":[115],"it":[118,210],"belongs":[119],"to,":[120],"remains":[121],"unchanged,":[122],"thus":[123],"significantly":[124],"reducing":[125],"number":[127],"points":[130],"need":[132],"transferred":[135],"between":[136],"CPU\u2019s":[138],"RAM":[139],"GPU\u2019s":[142],"global":[143],"enabling":[146],"very":[150],"efficiently":[151],"process":[152],"large":[153],"datasets.":[154],"Our":[155],"substantially":[159],"faster":[160,200],"implementation":[164,205,217],"standard":[166,176,203],"even":[169],"situations":[171],"when":[172],"application":[173],"feasible":[179],"because":[180],"fits":[184],"into":[185],"Experiments":[188],"show":[189],"ASB":[191],"up":[196],"15x":[198],"times":[199],"also":[211],"outperforms":[212],"NVIDIA\u2019s":[219],"open-source":[220],"RAPIDS":[221],"machine":[222],"learning":[223],"library":[224],"on":[225],"all":[226],"experiments.":[232]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4306735095","counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5}],"updated_date":"2024-11-28T07:00:00.600282","created_date":"2022-10-19"}