{"id":"https://openalex.org/W2783522158","doi":"https://doi.org/10.1109/bigdata.2017.8258024","title":"Micro-clustering by data polishing","display_name":"Micro-clustering by data polishing","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2783522158","doi":"https://doi.org/10.1109/bigdata.2017.8258024","mag":"2783522158"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2017.8258024","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2017.8258024","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 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/A5076101253","display_name":"Takeaki Uno","orcid":"https://orcid.org/0000-0001-7274-279X"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Takeaki Uno","raw_affiliation_strings":["National Institute of Informatics, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082268322","display_name":"Hiroki Maegawa","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hiroki Maegawa","raw_affiliation_strings":["KSK, Japan"],"affiliations":[{"raw_affiliation_string":"KSK, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114036442","display_name":"Takanobu Nakahara","orcid":null},"institutions":[{"id":"https://openalex.org/I85283370","display_name":"Senshu University","ror":"https://ror.org/03jzxkg37","country_code":"JP","type":"education","lineage":["https://openalex.org/I85283370"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takanobu Nakahara","raw_affiliation_strings":["Senshu University, Japan"],"affiliations":[{"raw_affiliation_string":"Senshu University, Japan","institution_ids":["https://openalex.org/I85283370"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086107781","display_name":"Yukinobu Hamuro","orcid":null},"institutions":[{"id":"https://openalex.org/I206011266","display_name":"Kwansei Gakuin University","ror":"https://ror.org/02qf2tx24","country_code":"JP","type":"education","lineage":["https://openalex.org/I206011266"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yukinobu Hamuro","raw_affiliation_strings":["Kwansei Gakuin University of Japan"],"affiliations":[{"raw_affiliation_string":"Kwansei Gakuin University of Japan","institution_ids":["https://openalex.org/I206011266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078196107","display_name":"Ryo Yoshinaka","orcid":"https://orcid.org/0000-0002-5175-465X"},"institutions":[{"id":"https://openalex.org/I201537933","display_name":"Tohoku University","ror":"https://ror.org/01dq60k83","country_code":"JP","type":"education","lineage":["https://openalex.org/I201537933"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryo Yoshinaka","raw_affiliation_strings":["Tohoku University, Japan"],"affiliations":[{"raw_affiliation_string":"Tohoku University, Japan","institution_ids":["https://openalex.org/I201537933"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024163301","display_name":"Makoto Tatsuta","orcid":null},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Makoto Tatsuta","raw_affiliation_strings":["National Institute of Informatics, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Japan","institution_ids":["https://openalex.org/I184597095"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5076101253"],"corresponding_institution_ids":["https://openalex.org/I184597095"],"apc_list":null,"apc_paid":null,"fwci":0.9751,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.82882532,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"5","issue":null,"first_page":"1012","last_page":"1018"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9998000264167786,"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":"Advanced Clustering Algorithms Research","score":0.9998000264167786,"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/T10064","display_name":"Complex Network Analysis Techniques","score":0.9986000061035156,"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/T10799","display_name":"Data Visualization and Analytics","score":0.9908999800682068,"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/cluster-analysis","display_name":"Cluster analysis","score":0.8284062147140503},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6763894557952881},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.628144383430481},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5958857536315918},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.4913999140262604},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.49056142568588257},{"id":"https://openalex.org/keywords/data-stream-clustering","display_name":"Data stream clustering","score":0.45011106133461},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.4317348599433899},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.414652556180954},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.39566653966903687},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.38955333828926086},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3848645091056824},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.16784816980361938}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8284062147140503},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6763894557952881},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.628144383430481},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5958857536315918},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.4913999140262604},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.49056142568588257},{"id":"https://openalex.org/C193143536","wikidata":"https://www.wikidata.org/wiki/Q5227360","display_name":"Data stream clustering","level":5,"score":0.45011106133461},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.4317348599433899},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.414652556180954},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39566653966903687},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.38955333828926086},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3848645091056824},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.16784816980361938},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata.2017.8258024","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2017.8258024","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1532325895","https://openalex.org/W1673310716","https://openalex.org/W1868111879","https://openalex.org/W1971421925","https://openalex.org/W2009723146","https://openalex.org/W2124166542","https://openalex.org/W2150102617","https://openalex.org/W2153472243","https://openalex.org/W2156094048","https://openalex.org/W4213009331","https://openalex.org/W6637131181","https://openalex.org/W6681875376"],"related_works":["https://openalex.org/W3144143113","https://openalex.org/W3120229345","https://openalex.org/W3022637481","https://openalex.org/W2371010743","https://openalex.org/W2393816671","https://openalex.org/W1999117613","https://openalex.org/W2356198087","https://openalex.org/W3186815950","https://openalex.org/W3168768270","https://openalex.org/W2970954390"],"abstract_inverted_index":{"We":[0,60,134],"address":[1],"the":[2,14,70,74,78,124,142,158,166,175,184],"problem":[3,15],"of":[4,13,22,48,51,57,126,160,168,177],"un-supervised":[5],"soft-clustering":[6],"that":[7,95,141],"we":[8],"call":[9],"micro-clustering.":[10],"The":[11,40,111,154],"aim":[12],"is":[16,129,144,170,187],"to":[17,26,81,98,121,131],"enumerate":[18],"all":[19],"groups":[20],"composed":[21],"records":[23,37],"strongly":[24],"related":[25],"each":[27,178],"other,":[28],"whereas":[29],"standard":[30],"clustering":[31,88],"methods":[32,42],"find":[33],"boundaries":[34],"at":[35],"which":[36],"are":[38,113,119,180],"few.":[39],"existing":[41],"have":[43],"several":[44],"weak":[45],"points;":[46],"generation":[47],"intractable":[49],"amounts":[50],"clusters,":[52],"biased":[53],"size":[54],"distributions,":[55],"lack":[56],"robustness,":[58],"etc.":[59],"propose":[61,136],"a":[62],"new":[63],"methodology":[64],"data":[65,75,79,90],"polishing.":[66],"Data":[67],"polishing":[68,91],"clarifies":[69],"cluster":[71],"structures":[72],"in":[73,107,146],"by":[76,100],"perturbating":[77],"according":[80],"feasible":[82],"hypothesis.":[83],"More":[84],"precisely,":[85],"for":[86,150],"graph":[87],"problems,":[89],"replaces":[92],"dense":[93,109],"subgraphs":[94],"would":[96],"correspond":[97],"clusters":[99,112],"cliques,":[101,117],"and":[102,123,163,183],"deletes":[103],"edges":[104],"not":[105],"included":[106],"any":[108],"subgraph.":[110],"clarified":[114],"as":[115,173],"maximal":[116,127],"thus":[118],"easy":[120],"find,":[122],"number":[125,167],"cliques":[128],"reduced":[130],"tractable":[132],"numbers.":[133],"also":[135],"an":[137],"efficient":[138],"algorithm":[139],"so":[140],"computation":[143,185],"done":[145],"few":[147],"minutes":[148],"even":[149],"large":[151],"scale":[152],"data.":[153],"computational":[155],"experiments":[156],"demonstrate":[157],"efficiency":[159],"our":[161],"formulation":[162],"algorithm,":[164],"i.e.,":[165],"solutions":[169],"small,":[171],"such":[172],"1,000,":[174],"members":[176],"group":[179],"deeply":[181],"related,":[182],"time":[186],"short.":[188]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}