{"id":"https://openalex.org/W2744226525","doi":"https://doi.org/10.1145/3097983.3098098","title":"PAMAE","display_name":"PAMAE","publication_year":2017,"publication_date":"2017-08-04","ids":{"openalex":"https://openalex.org/W2744226525","doi":"https://doi.org/10.1145/3097983.3098098","mag":"2744226525"},"language":"en","primary_location":{"id":"doi:10.1145/3097983.3098098","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3097983.3098098","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","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/A5033909285","display_name":"Hwanjun Song","orcid":"https://orcid.org/0000-0002-1105-0818"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Hwanjun Song","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology, Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101805827","display_name":"Jae-Gil Lee","orcid":"https://orcid.org/0000-0002-8711-7732"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jae-Gil Lee","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology, Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035744252","display_name":"Wook-Shin Han","orcid":"https://orcid.org/0000-0001-9206-9563"},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Wook-Shin Han","raw_affiliation_strings":["POSTECH, Pohang, South Korea"],"affiliations":[{"raw_affiliation_string":"POSTECH, Pohang, South Korea","institution_ids":["https://openalex.org/I123900574"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5033909285"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":3.7355,"has_fulltext":false,"cited_by_count":41,"citation_normalized_percentile":{"value":0.94402628,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1087","last_page":"1096"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11106","display_name":"Data Management and Algorithms","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9995999932289124,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.8267676830291748},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6281049251556396},{"id":"https://openalex.org/keywords/medoid","display_name":"Medoid","score":0.6007676124572754},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.6003046035766602},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5381286144256592},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.4999842643737793},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4828377366065979},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.44945377111434937},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1396089792251587}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8267676830291748},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6281049251556396},{"id":"https://openalex.org/C63085389","wikidata":"https://www.wikidata.org/wiki/Q4287912","display_name":"Medoid","level":3,"score":0.6007676124572754},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.6003046035766602},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5381286144256592},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.4999842643737793},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4828377366065979},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.44945377111434937},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1396089792251587},{"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3097983.3098098","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3097983.3098098","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G4936975077","display_name":null,"funder_award_id":"2015R1A1A1A05001475","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W87092222","https://openalex.org/W208128215","https://openalex.org/W845171161","https://openalex.org/W1493454437","https://openalex.org/W1697570164","https://openalex.org/W1967810725","https://openalex.org/W1968569790","https://openalex.org/W1969144558","https://openalex.org/W1969463951","https://openalex.org/W2002360418","https://openalex.org/W2016239948","https://openalex.org/W2025753535","https://openalex.org/W2034616054","https://openalex.org/W2048442462","https://openalex.org/W2072487419","https://openalex.org/W2082503527","https://openalex.org/W2083620785","https://openalex.org/W2093071433","https://openalex.org/W2109181422","https://openalex.org/W2109820980","https://openalex.org/W2111741784","https://openalex.org/W2113671562","https://openalex.org/W2122516862","https://openalex.org/W2126626732","https://openalex.org/W2133962824","https://openalex.org/W2140190241","https://openalex.org/W2170735271","https://openalex.org/W2183417208","https://openalex.org/W2217927657","https://openalex.org/W2237415976","https://openalex.org/W2800198128","https://openalex.org/W2999729612","https://openalex.org/W3020847247","https://openalex.org/W4230765542"],"related_works":["https://openalex.org/W3133849001","https://openalex.org/W2022056881","https://openalex.org/W2766461310","https://openalex.org/W4247566972","https://openalex.org/W4388692845","https://openalex.org/W3202731209","https://openalex.org/W3211874991","https://openalex.org/W2587710587","https://openalex.org/W2100425112","https://openalex.org/W3037673319"],"abstract_inverted_index":{"The":[0,125,205,233],"k-medoids":[1,45,67],"algorithm":[2],"is":[3,14,107,123],"one":[4],"of":[5,29,43,57,121,152,177,213],"the":[6,24,40,44,55,135,153,175,219,229],"best-known":[7],"clustering":[8,224],"algorithms.":[9],"Despite":[10],"this,":[11],"however,":[12],"it":[13],"not":[15],"as":[16,23,185,187,226,228],"widely":[17],"used":[18],"for":[19],"big":[20],"data":[21,196,237],"analytics":[22],"k-means":[25],"algorithm,":[26,46,68],"mainly":[27],"because":[28],"its":[30],"high":[31,76,79,93],"computational":[32],"complexity.":[33],"Many":[34],"studies":[35,50],"have":[36,51],"attempted":[37],"to":[38,91,108,157,173],"solve":[39],"efficiency":[41,53],"problem":[42],"but":[47,95],"all":[48],"such":[49],"improved":[52],"at":[54,218,240],"expense":[56],"accuracy.":[58],"In":[59,171],"this":[60,149],"paper,":[61],"we":[62,70,180],"propose":[63],"a":[64,223],"novel":[65],"parallel":[66,115,118,215],"which":[69,122],"call":[71],"PAMAE,":[72],"that":[73,148,161,208],"achieves":[74],"both":[75],"accuracy":[77],"and":[78,86,117,134,189,236],"efficiency.":[80],"We":[81],"identify":[82],"two":[83,113,154],"factors---\"global":[84],"search\"":[85],"\"entire":[87],"data\"---that":[88],"are":[89,96,238],"essential":[90],"achieving":[92],"accuracy,":[94],"also":[97],"very":[98],"time-consuming":[99],"if":[100],"considered":[101],"simultaneously.":[102],"Thus,":[103],"our":[104,178],"key":[105],"idea":[106],"apply":[109],"them":[110],"individually":[111],"through":[112],"phases:":[114],"seeding":[116],"refinement,":[119],"neither":[120],"costly.":[124],"first":[126],"phase":[127,137],"performs":[128,138],"global":[129,166],"search":[130,140,167],"over":[131,141,168],"sampled":[132],"data,":[133],"second":[136],"local":[139],"entire":[142,169],"data.":[143,170],"Our":[144],"theoretical":[145],"analysis":[146],"proves":[147],"serial":[150],"execution":[151],"phases":[155],"leads":[156],"an":[158],"accurate":[159],"solution":[160],"would":[162],"be":[163],"achieved":[164],"by":[165],"order":[172],"validate":[174],"merit":[176],"approach,":[179],"implement":[181],"PAMAE":[182,209],"on":[183,198],"Spark":[184],"well":[186],"Hadoop":[188],"conduct":[190],"extensive":[191],"experiments":[192],"using":[193],"various":[194],"real-world":[195],"sets":[197],"12":[199],"Microsoft":[200],"Azure":[201],"machines":[202],"(48":[203],"cores).":[204],"results":[206],"show":[207],"significantly":[210],"outperforms":[211],"most":[212],"recent":[214],"algorithms":[216],"and,":[217],"same":[220],"time,":[221],"produces":[222],"quality":[225],"comparable":[227],"previous":[230],"most-accurate":[231],"algorithm.":[232],"source":[234],"code":[235],"available":[239],"https://github.com/jaegil/k-Medoid.":[241]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2}],"updated_date":"2026-03-14T08:43:22.919905","created_date":"2017-08-17T00:00:00"}