{"id":"https://openalex.org/W4391841672","doi":"https://doi.org/10.1007/s11063-024-11444-z","title":"Large-Scale Clustering on 100\u00a0M-Scale Datasets Using a Single T4 GPU via Recall KNN and Subgraph Segmentation","display_name":"Large-Scale Clustering on 100\u00a0M-Scale Datasets Using a Single T4 GPU via Recall KNN and Subgraph Segmentation","publication_year":2024,"publication_date":"2024-02-15","ids":{"openalex":"https://openalex.org/W4391841672","doi":"https://doi.org/10.1007/s11063-024-11444-z"},"language":"en","primary_location":{"id":"doi:10.1007/s11063-024-11444-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11063-024-11444-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11063-024-11444-z.pdf","source":{"id":"https://openalex.org/S140962798","display_name":"Neural Processing Letters","issn_l":"1370-4621","issn":["1370-4621","1573-773X"],"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/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Processing Letters","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11063-024-11444-z.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100396419","display_name":"Junjie Liu","orcid":"https://orcid.org/0000-0001-7373-9074"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]},{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Junjie Liu","raw_affiliation_strings":["Alibaba DAMO Academy, Hangzhou, China","Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Alibaba DAMO Academy, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028024624","display_name":"Rongxin Jiang","orcid":"https://orcid.org/0000-0001-7901-3047"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongxin Jiang","raw_affiliation_strings":["Zhejiang University Embedded System Engineering Research Center, Ministry of Education of China, Hangzhou, China","Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University Embedded System Engineering Research Center, Ministry of Education of China, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100671618","display_name":"Xuesong Liu","orcid":"https://orcid.org/0000-0001-8549-0368"},"institutions":[{"id":"https://openalex.org/I4210141176","display_name":"Communication University of Zhejiang","ror":"https://ror.org/04t7gxr16","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210141176"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuesong Liu","raw_affiliation_strings":["Zhejiang Provincial Key Laboratory for Network Multimedia Technologies, Hangzhou, China","Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang Provincial Key Laboratory for Network Multimedia Technologies, Hangzhou, China","institution_ids":["https://openalex.org/I4210141176"]},{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100403433","display_name":"Fan Zhou","orcid":"https://orcid.org/0000-0002-0900-6965"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]},{"id":"https://openalex.org/I4210141176","display_name":"Communication University of Zhejiang","ror":"https://ror.org/04t7gxr16","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210141176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Zhou","raw_affiliation_strings":["Zhejiang Provincial Key Laboratory for Network Multimedia Technologies, Hangzhou, China","Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang Provincial Key Laboratory for Network Multimedia Technologies, Hangzhou, China","institution_ids":["https://openalex.org/I4210141176"]},{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008526350","display_name":"Yaowu Chen","orcid":"https://orcid.org/0000-0002-6037-0631"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaowu Chen","raw_affiliation_strings":["Zhejiang University Embedded System Engineering Research Center, Ministry of Education of China, Hangzhou, China","Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University Embedded System Engineering Research Center, Ministry of Education of China, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022877637","display_name":"Chen Shen","orcid":"https://orcid.org/0000-0002-7534-0830"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Shen","raw_affiliation_strings":["Alibaba DAMO Academy, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Alibaba DAMO Academy, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100396419"],"corresponding_institution_ids":["https://openalex.org/I45928872","https://openalex.org/I76130692"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":0.2408,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.44946851,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"56","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9990000128746033,"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"}},"topics":[{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9990000128746033,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9990000128746033,"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/T10057","display_name":"Face and Expression Recognition","score":0.9988999962806702,"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/scale","display_name":"Scale (ratio)","score":0.6473071575164795},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6434977650642395},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6424287557601929},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6304841041564941},{"id":"https://openalex.org/keywords/computational-intelligence","display_name":"Computational intelligence","score":0.6223481297492981},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.49250563979148865},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4676361083984375},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.4484701454639435},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.43576177954673767},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3779435157775879},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.07526597380638123},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.0662495493888855}],"concepts":[{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.6473071575164795},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6434977650642395},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6424287557601929},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6304841041564941},{"id":"https://openalex.org/C139502532","wikidata":"https://www.wikidata.org/wiki/Q1122090","display_name":"Computational intelligence","level":2,"score":0.6223481297492981},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.49250563979148865},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4676361083984375},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.4484701454639435},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.43576177954673767},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3779435157775879},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.07526597380638123},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0662495493888855},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s11063-024-11444-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11063-024-11444-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11063-024-11444-z.pdf","source":{"id":"https://openalex.org/S140962798","display_name":"Neural Processing Letters","issn_l":"1370-4621","issn":["1370-4621","1573-773X"],"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/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Processing Letters","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s11063-024-11444-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11063-024-11444-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11063-024-11444-z.pdf","source":{"id":"https://openalex.org/S140962798","display_name":"Neural Processing Letters","issn_l":"1370-4621","issn":["1370-4621","1573-773X"],"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/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Processing Letters","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5389520754","display_name":null,"funder_award_id":"LDT23F01013F01","funder_id":"https://openalex.org/F4320338464","funder_display_name":"Natural Science Foundation of Zhejiang Province"}],"funders":[{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null},{"id":"https://openalex.org/F4320338464","display_name":"Natural Science Foundation of Zhejiang Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4391841672.pdf"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W239253814","https://openalex.org/W569478347","https://openalex.org/W2072240081","https://openalex.org/W2120636855","https://openalex.org/W2121947440","https://openalex.org/W2124209874","https://openalex.org/W2150593711","https://openalex.org/W2165232124","https://openalex.org/W2515770085","https://openalex.org/W2562931712","https://openalex.org/W2564022854","https://openalex.org/W2605170010","https://openalex.org/W2791746273","https://openalex.org/W2890125629","https://openalex.org/W2930556772","https://openalex.org/W2944238451","https://openalex.org/W2963469388","https://openalex.org/W2965744772","https://openalex.org/W2998702515","https://openalex.org/W3035669277","https://openalex.org/W3102802330","https://openalex.org/W3119461691","https://openalex.org/W3158852672","https://openalex.org/W3167774079","https://openalex.org/W3173718098","https://openalex.org/W3217435001","https://openalex.org/W4210942381","https://openalex.org/W4297964641","https://openalex.org/W4308193422","https://openalex.org/W4311457624","https://openalex.org/W4312402191","https://openalex.org/W4312459443","https://openalex.org/W4318701508","https://openalex.org/W6600424091","https://openalex.org/W6603957568"],"related_works":["https://openalex.org/W4330338194","https://openalex.org/W2804364458","https://openalex.org/W2118758177","https://openalex.org/W2153520307","https://openalex.org/W4298130764","https://openalex.org/W2151459719","https://openalex.org/W2132641928","https://openalex.org/W2358294942","https://openalex.org/W2072289174","https://openalex.org/W4367460280"],"abstract_inverted_index":{"Abstract":[0],"Despite":[1],"the":[2,42,76,96,111,119,147,154,162,166,183,210,218],"promising":[3],"progress":[4],"that":[5,181,226],"has":[6],"been":[7],"made,":[8],"large-scale":[9,53,57,80,115,230],"clustering":[10,54,58,69,72,116,212,231],"tasks":[11,55],"still":[12],"face":[13],"various":[14],"challenges:":[15],"(i)":[16],"high":[17],"time":[18,134],"and":[19,33,62,104,135,191,198,209,236],"space":[20,136],"complexity":[21,137],"in":[22,114,233],"K-nearest":[23],"neighbors":[24],"(KNN),":[25],"which":[26,74],"is":[27,122,150,178,194,214],"often":[28],"overlooked":[29],"by":[30,39,216],"most":[31],"methods,":[32,176],"(ii)":[34],"low":[35],"recall":[36,60,101,120,163,167,189],"rate":[37,168],"caused":[38],"simply":[40],"splitting":[41],"dataset.":[43],"In":[44],"this":[45],"paper,":[46],"we":[47],"propose":[48,100],"a":[49,87,195],"novel":[50],"framework":[51],"for":[52],"named":[56],"via":[59],"KNN":[61,102,121,190],"subgraph":[63,105,148,192],"segmentation":[64,106,149,193],"(LS-RKSS)":[65],"to":[66,83,108,124,139,152],"perform":[67,125],"faster":[68],"with":[70,91,132],"guaranteed":[71],"performance,":[73],"embraces":[75],"ability":[77],"of":[78,95,144,169,220],"handling":[79],"data":[81],"up":[82],"100":[84],"million":[85],"using":[86,188],"single":[88],"T4":[89],"GPU":[90],"less":[92],"than":[93],"10%":[94],"running":[97],"time.":[98],"We":[99],"(RKNN)":[103],"(SS)":[107],"effectively":[109],"address":[110],"primary":[112],"challenges":[113],"tasks.":[117],"Firstly,":[118],"proposed":[123,151],"efficient":[126],"similarity":[127],"search":[128,142,175],"among":[129],"dense":[130],"vectors":[131],"lower":[133],"compared":[138],"traditional":[140,173],"exact":[141,174],"methods":[143,232],"KNN.":[145,164],"Then,":[146],"split":[153],"whole":[155],"dataset":[156,184],"into":[157,185],"multiple":[158,186],"subgraphs":[159,187],"based":[160,171],"on":[161,172,206],"Given":[165],"RKNN":[170],"it":[177],"theoretically":[179],"proved":[180],"dividing":[182],"more":[196],"reasonable":[197],"effective":[199],"approach.":[200],"Finally,":[201],"clusters":[202],"are":[203],"generated":[204],"independently":[205],"each":[207],"subgraph,":[208],"final":[211],"result":[213],"obtained":[215],"combining":[217],"results":[219],"all":[221],"subgraphs.":[222],"Extensive":[223],"experiments":[224],"demonstrate":[225],"LS-RKSS":[227],"outperforms":[228],"previous":[229],"both":[234],"effectiveness":[235],"efficiency.":[237]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}