{"id":"https://openalex.org/W2146598701","doi":"https://doi.org/10.1145/1014052.1014112","title":"An objective evaluation criterion for clustering","display_name":"An objective evaluation criterion for clustering","publication_year":2004,"publication_date":"2004-08-22","ids":{"openalex":"https://openalex.org/W2146598701","doi":"https://doi.org/10.1145/1014052.1014112","mag":"2146598701"},"language":"en","primary_location":{"id":"doi:10.1145/1014052.1014112","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1014052.1014112","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the tenth 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/A5014459472","display_name":"Arindam Banerjee","orcid":"https://orcid.org/0000-0002-7856-5699"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Arindam Banerjee","raw_affiliation_strings":["University of Texas at Austin, Austin, TX"],"affiliations":[{"raw_affiliation_string":"University of Texas at Austin, Austin, TX","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005003250","display_name":"John Langford","orcid":"https://orcid.org/0000-0002-9811-3550"},"institutions":[{"id":"https://openalex.org/I160992636","display_name":"Toyota Technological Institute at Chicago","ror":"https://ror.org/02sn5gb64","country_code":"US","type":"education","lineage":["https://openalex.org/I160992636"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John Langford","raw_affiliation_strings":["Toyota Technological Institute, Chicago, IL"],"affiliations":[{"raw_affiliation_string":"Toyota Technological Institute, Chicago, IL","institution_ids":["https://openalex.org/I160992636"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5014459472"],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":6.0077,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.96117818,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"515","last_page":"520"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9994999766349792,"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":0.9994999766349792,"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/T11269","display_name":"Algorithms and Data Compression","score":0.998199999332428,"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/T11106","display_name":"Data Management and Algorithms","score":0.9979000091552734,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.8610663414001465},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7226371169090271},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.606850266456604},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5425150990486145},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5321744084358215},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5069082379341125},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.45430973172187805},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.43966957926750183},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4145430624485016},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.41227108240127563},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35779520869255066}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8610663414001465},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7226371169090271},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.606850266456604},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5425150990486145},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5321744084358215},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5069082379341125},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.45430973172187805},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.43966957926750183},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4145430624485016},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.41227108240127563},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35779520869255066},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1014052.1014112","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1014052.1014112","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1479895691","https://openalex.org/W1790954942","https://openalex.org/W1971784203","https://openalex.org/W2123504323","https://openalex.org/W2129070834","https://openalex.org/W2138570191","https://openalex.org/W2149521737","https://openalex.org/W2319660501","https://openalex.org/W2963673689","https://openalex.org/W6628649286","https://openalex.org/W6770641979"],"related_works":["https://openalex.org/W3022637481","https://openalex.org/W3144143113","https://openalex.org/W3120229345","https://openalex.org/W1999117613","https://openalex.org/W2393816671","https://openalex.org/W3039964395","https://openalex.org/W2954170735","https://openalex.org/W2607902515","https://openalex.org/W2040929534","https://openalex.org/W3168768270"],"abstract_inverted_index":{"We":[0],"propose":[1],"and":[2],"test":[3,88],"an":[4,66],"objective":[5,67],"criterion":[6],"for":[7],"evaluation":[8],"of":[9,54,61],"clustering":[10,16],"performance:":[11],"How":[12],"well":[13],"does":[14],"a":[15,23,36,51],"algorithm":[17],"run":[18],"on":[19,73,87,91],"unlabeled":[20],"data":[21,45],"aid":[22],"classification":[24],"algorithm?":[25],"The":[26],"accuracy":[27],"is":[28],"quantified":[29],"using":[30],"the":[31,44,62],"PAC-MDL":[32],"bound":[33],"[3]":[34],"in":[35,83],"semisupervised":[37],"setting.":[38],"Clustering":[39],"algorithms":[40],"which":[41],"naturally":[42],"separate":[43],"according":[46],"to":[47,65],"(hidden)":[48],"labels":[49],"with":[50],"small":[52],"number":[53],"clusters":[55],"perform":[56],"well.":[57],"A":[58],"simple":[59],"extension":[60],"argument":[63],"leads":[64],"model":[68],"selection":[69],"method.":[70],"Experimental":[71],"results":[72,82],"text":[74],"analysis":[75],"datasets":[76],"demonstrate":[77],"that":[78],"this":[79],"approach":[80],"empirically":[81],"very":[84],"competitive":[85],"bounds":[86],"set":[89],"performance":[90],"natural":[92],"datasets.":[93]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}