{"id":"https://openalex.org/W4408145475","doi":"https://doi.org/10.1109/tpami.2025.3548011","title":"Measuring the Validity of Clustering Validation Datasets","display_name":"Measuring the Validity of Clustering Validation Datasets","publication_year":2025,"publication_date":"2025-03-04","ids":{"openalex":"https://openalex.org/W4408145475","doi":"https://doi.org/10.1109/tpami.2025.3548011","pmid":"https://pubmed.ncbi.nlm.nih.gov/40036522"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2025.3548011","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3548011","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5101506748","display_name":"Hyeon Jeon","orcid":"https://orcid.org/0000-0002-9659-2922"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyeon Jeon","raw_affiliation_strings":["Seoul National University, Seoul, South Korea","Seoul National University, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-9659-2922","affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Seoul National University, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000064618","display_name":"Micha\u00ebl Aupetit","orcid":"https://orcid.org/0000-0001-6321-5242"},"institutions":[{"id":"https://openalex.org/I4210144839","display_name":"Hamad bin Khalifa University","ror":"https://ror.org/03eyq4y97","country_code":"QA","type":"education","lineage":["https://openalex.org/I4210144839"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Micha\u00ebl Aupetit","raw_affiliation_strings":["Qatar Computing Research Institute, Hamad Bin Khalifa University, Doha, Qatar","Qatar Computing Research Institute, Hamad Bin Khalifa University, Qatar"],"raw_orcid":"https://orcid.org/0000-0001-6321-5242","affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute, Hamad Bin Khalifa University, Doha, Qatar","institution_ids":["https://openalex.org/I4210144839"]},{"raw_affiliation_string":"Qatar Computing Research Institute, Hamad Bin Khalifa University, Qatar","institution_ids":["https://openalex.org/I4210144839"]}]},{"author_position":"middle","author":{"id":null,"display_name":"DongHwa Shin","orcid":"https://orcid.org/0000-0001-9460-809X"},"institutions":[{"id":"https://openalex.org/I161024014","display_name":"Kwangwoon University","ror":"https://ror.org/02e9zc863","country_code":"KR","type":"education","lineage":["https://openalex.org/I161024014"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"DongHwa Shin","raw_affiliation_strings":["Kwangwoon University, Seoul, South Korea","Kwangwoon University, South Korea"],"raw_orcid":"https://orcid.org/0000-0001-9460-809X","affiliations":[{"raw_affiliation_string":"Kwangwoon University, Seoul, South Korea","institution_ids":["https://openalex.org/I161024014"]},{"raw_affiliation_string":"Kwangwoon University, South Korea","institution_ids":["https://openalex.org/I161024014"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091578590","display_name":"Aeri Cho","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Aeri Cho","raw_affiliation_strings":["Seoul National University, Seoul, South Korea","Seoul National University, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-4027-2583","affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Seoul National University, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075564332","display_name":"Seokhyeon Park","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seokhyeon Park","raw_affiliation_strings":["Seoul National University, Seoul, South Korea","Seoul National University, South Korea"],"raw_orcid":"https://orcid.org/0009-0003-1685-4027","affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Seoul National University, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012388103","display_name":"Jinwook Seo","orcid":"https://orcid.org/0000-0002-7734-822X"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jinwook Seo","raw_affiliation_strings":["Seoul National University, Seoul, South Korea","Seoul National University, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-7734-822X","affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Seoul National University, South Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":14.0702,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.98545958,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"47","issue":"6","first_page":"5045","last_page":"5058"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.8705000281333923,"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":0.8705000281333923,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6821227073669434},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6606841683387756},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5900049805641174},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4345918297767639},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42998093366622925}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6821227073669434},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6606841683387756},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5900049805641174},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4345918297767639},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42998093366622925}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2025.3548011","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3548011","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:40036522","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40036522","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G277447885","display_name":null,"funder_award_id":"2023R1A2C200520911","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320321292","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W143174683","https://openalex.org/W151377110","https://openalex.org/W1460189015","https://openalex.org/W1496153843","https://openalex.org/W1523794535","https://openalex.org/W1599454686","https://openalex.org/W1672197616","https://openalex.org/W1697154133","https://openalex.org/W1964966468","https://openalex.org/W1977556410","https://openalex.org/W1987971958","https://openalex.org/W1988608305","https://openalex.org/W1993962865","https://openalex.org/W1995045912","https://openalex.org/W1996747841","https://openalex.org/W2002767255","https://openalex.org/W2029064186","https://openalex.org/W2049810170","https://openalex.org/W2051224630","https://openalex.org/W2083620785","https://openalex.org/W2085487226","https://openalex.org/W2095897464","https://openalex.org/W2096879261","https://openalex.org/W2108323654","https://openalex.org/W2113586398","https://openalex.org/W2129630294","https://openalex.org/W2133916049","https://openalex.org/W2140405352","https://openalex.org/W2143867397","https://openalex.org/W2162833336","https://openalex.org/W2168532736","https://openalex.org/W2295598076","https://openalex.org/W2432267564","https://openalex.org/W2740924709","https://openalex.org/W2766176203","https://openalex.org/W2781979348","https://openalex.org/W2883725317","https://openalex.org/W2948646817","https://openalex.org/W2960826148","https://openalex.org/W2964051179","https://openalex.org/W2995497672","https://openalex.org/W3114559164","https://openalex.org/W3128396846","https://openalex.org/W3173985852","https://openalex.org/W4200108042","https://openalex.org/W4235169531","https://openalex.org/W4312714033","https://openalex.org/W4385245566","https://openalex.org/W4388286168","https://openalex.org/W4388286222","https://openalex.org/W4391488432","https://openalex.org/W4400786623","https://openalex.org/W4401042982","https://openalex.org/W4404238839","https://openalex.org/W4409748645","https://openalex.org/W6635035540","https://openalex.org/W6676671362","https://openalex.org/W6678911119","https://openalex.org/W6680970901","https://openalex.org/W6761343230","https://openalex.org/W6838978922","https://openalex.org/W6858356640","https://openalex.org/W7006806681"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2033914206","https://openalex.org/W2042327336"],"abstract_inverted_index":{"Clustering":[0],"techniques":[1],"are":[2,11,77],"often":[3],"validated":[4],"using":[5,192],"benchmark":[6],"datasets":[7,45,186],"where":[8],"class":[9,21,55],"labels":[10,22,56],"used":[12,147],"as":[13,91],"ground-truth":[14],"clusters.":[15,59],"However,":[16],"depending":[17],"on":[18],"the":[19,27,73,153,167,185],"datasets,":[20],"may":[23],"not":[24,78,117],"align":[25],"with":[26],"actual":[28,58],"data":[29,115],"clusters,":[30],"and":[31,43,93,98,139,155,160,178],"such":[32],"misalignment":[33],"hampers":[34],"accurate":[35],"validation.":[36,202],"Therefore,":[37],"it":[38],"is":[39],"essential":[40],"to":[41,80,96,111,119,131,135,143,195],"evaluate":[42,97],"compare":[44,67,99],"regarding":[46],"their":[47,54],"cluster-label":[48],"matching":[49],"(CLM),":[50],"i.e.,":[51],"how":[52],"well":[53],"match":[57],"Internal":[60],"validation":[61,109],"measures":[62,110],"(IVMs),":[63],"like":[64],"Silhouette,":[65],"can":[66,187],"CLM":[68,100,175],"over":[69],"different":[70,84],"labeling":[71],"of":[72,114,157],"same":[74],"dataset,":[75],"but":[76],"designed":[79],"do":[81],"so":[82],"across":[83,101,179],"datasets.":[85,102,180],"We":[86,103,181],"thus":[87],"introduce":[88],"Adjusted":[89],"IVMs":[90,165],"fast":[92],"reliable":[94,198],"methods":[95],"establish":[104],"four":[105],"axioms":[106],"that":[107,163,184],"require":[108],"be":[112,188],"independent":[113],"properties":[116],"related":[118],"cluster":[120],"structure":[121],"(e.g.,":[122],"dimensionality,":[123],"dataset":[124],"size).":[125],"Then,":[126],"we":[127],"develop":[128],"standardized":[129],"protocols":[130,142,159],"convert":[132],"any":[133],"IVM":[134],"satisfy":[136],"these":[137,141],"axioms,":[138],"use":[140],"adjust":[144],"six":[145],"widely":[146],"IVMs.":[148],"Quantitative":[149],"experiments":[150],"(1)":[151],"verify":[152],"necessity":[154],"effectiveness":[156],"our":[158,193],"(2)":[161],"show":[162,183],"adjusted":[164],"outperform":[166],"competitors,":[168],"including":[169],"standard":[170],"IVMs,":[171],"in":[172],"accurately":[173],"evaluating":[174],"both":[176],"within":[177],"also":[182],"filtered":[189],"or":[190],"improved":[191],"method":[194],"form":[196],"more":[197],"benchmarks":[199],"for":[200],"clustering":[201]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}