{"id":"https://openalex.org/W2039048398","doi":"https://doi.org/10.1145/1835804.1835908","title":"Redefining class definitions using constraint-based clustering","display_name":"Redefining class definitions using constraint-based clustering","publication_year":2010,"publication_date":"2010-07-25","ids":{"openalex":"https://openalex.org/W2039048398","doi":"https://doi.org/10.1145/1835804.1835908","mag":"2039048398"},"language":"en","primary_location":{"id":"doi:10.1145/1835804.1835908","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1835804.1835908","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th 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/A5047328697","display_name":"Dan Preston","orcid":null},"institutions":[{"id":"https://openalex.org/I121934306","display_name":"Tufts University","ror":"https://ror.org/05wvpxv85","country_code":"US","type":"education","lineage":["https://openalex.org/I121934306"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Dan R. Preston","raw_affiliation_strings":["Tufts University, Medford, MA, USA","Tufts University, Medford, MA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Tufts University, Medford, MA, USA","institution_ids":["https://openalex.org/I121934306"]},{"raw_affiliation_string":"Tufts University, Medford, MA, USA#TAB#","institution_ids":["https://openalex.org/I121934306"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045379675","display_name":"Carla E. Brodley","orcid":"https://orcid.org/0009-0008-2134-6285"},"institutions":[{"id":"https://openalex.org/I121934306","display_name":"Tufts University","ror":"https://ror.org/05wvpxv85","country_code":"US","type":"education","lineage":["https://openalex.org/I121934306"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carla E. Brodley","raw_affiliation_strings":["Tufts University, Medford, MA, USA","Tufts University, Medford, MA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Tufts University, Medford, MA, USA","institution_ids":["https://openalex.org/I121934306"]},{"raw_affiliation_string":"Tufts University, Medford, MA, USA#TAB#","institution_ids":["https://openalex.org/I121934306"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013618541","display_name":"Roni Khardon","orcid":null},"institutions":[{"id":"https://openalex.org/I121934306","display_name":"Tufts University","ror":"https://ror.org/05wvpxv85","country_code":"US","type":"education","lineage":["https://openalex.org/I121934306"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Roni Khardon","raw_affiliation_strings":["Tufts University, Medford, MA, USA","Tufts University, Medford, MA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Tufts University, Medford, MA, USA","institution_ids":["https://openalex.org/I121934306"]},{"raw_affiliation_string":"Tufts University, Medford, MA, USA#TAB#","institution_ids":["https://openalex.org/I121934306"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032477563","display_name":"Damien Sulla\u2010Menashe","orcid":"https://orcid.org/0000-0002-0435-6114"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Damien Sulla-Menashe","raw_affiliation_strings":["Boston University, Boston, MA, USA","Boston University , Boston , MA , USA"],"affiliations":[{"raw_affiliation_string":"Boston University, Boston, MA, USA","institution_ids":[]},{"raw_affiliation_string":"Boston University , Boston , MA , USA","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005834311","display_name":"M. A. Friedl","orcid":"https://orcid.org/0000-0001-6899-2948"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Friedl","raw_affiliation_strings":["Boston University, Boston, MA, USA","Boston University , Boston , MA , USA"],"affiliations":[{"raw_affiliation_string":"Boston University, Boston, MA, USA","institution_ids":[]},{"raw_affiliation_string":"Boston University , Boston , MA , USA","institution_ids":["https://openalex.org/I111088046"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5047328697"],"corresponding_institution_ids":["https://openalex.org/I121934306"],"apc_list":null,"apc_paid":null,"fwci":1.3486,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.80146534,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"823","last_page":"832"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9959999918937683,"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":0.9959999918937683,"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":0.9915000200271606,"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/T10757","display_name":"Geographic Information Systems Studies","score":0.9904999732971191,"subfield":{"id":"https://openalex.org/subfields/3305","display_name":"Geography, Planning and Development"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6491369009017944},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6440834403038025},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5857351422309875},{"id":"https://openalex.org/keywords/constrained-clustering","display_name":"Constrained clustering","score":0.5059816241264343},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5003662109375},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4923592805862427},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.46668869256973267},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.4566066265106201},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4316122531890869},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.35056859254837036},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3494705259799957},{"id":"https://openalex.org/keywords/fuzzy-clustering","display_name":"Fuzzy clustering","score":0.23880061507225037},{"id":"https://openalex.org/keywords/canopy-clustering-algorithm","display_name":"Canopy clustering algorithm","score":0.12173491716384888}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6491369009017944},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6440834403038025},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5857351422309875},{"id":"https://openalex.org/C27964816","wikidata":"https://www.wikidata.org/wiki/Q5164359","display_name":"Constrained clustering","level":5,"score":0.5059816241264343},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5003662109375},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4923592805862427},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.46668869256973267},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.4566066265106201},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4316122531890869},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35056859254837036},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3494705259799957},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.23880061507225037},{"id":"https://openalex.org/C104047586","wikidata":"https://www.wikidata.org/wiki/Q5033439","display_name":"Canopy clustering algorithm","level":4,"score":0.12173491716384888}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1835804.1835908","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1835804.1835908","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6600000262260437,"display_name":"Life in Land","id":"https://metadata.un.org/sdg/15"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1497193185","https://openalex.org/W1500470240","https://openalex.org/W1516407653","https://openalex.org/W1523293200","https://openalex.org/W1545632541","https://openalex.org/W1592305655","https://openalex.org/W1601705331","https://openalex.org/W1967768115","https://openalex.org/W1979153668","https://openalex.org/W1992402718","https://openalex.org/W2057064882","https://openalex.org/W2057765075","https://openalex.org/W2102524069","https://openalex.org/W2107061852","https://openalex.org/W2121025662","https://openalex.org/W2126367746","https://openalex.org/W2127218421","https://openalex.org/W2127559745","https://openalex.org/W2132914434","https://openalex.org/W2134089414","https://openalex.org/W2142635246","https://openalex.org/W2148687775","https://openalex.org/W2148694408","https://openalex.org/W2168175751","https://openalex.org/W2169422482","https://openalex.org/W2610360795","https://openalex.org/W2802533528","https://openalex.org/W2999905431","https://openalex.org/W4292023222"],"related_works":["https://openalex.org/W2951567704","https://openalex.org/W83259245","https://openalex.org/W2605343873","https://openalex.org/W2535986621","https://openalex.org/W2109624221","https://openalex.org/W2075698704","https://openalex.org/W569672973","https://openalex.org/W3034747430","https://openalex.org/W4229936142","https://openalex.org/W3206392503"],"abstract_inverted_index":{"Two":[0],"aspects":[1],"are":[2,51,80,277],"crucial":[3],"when":[4],"constructing":[5],"any":[6],"real":[7],"world":[8],"supervised":[9],"classification":[10,68,283],"task:":[11],"the":[12,22,26,36,53,57,70,105,109,113,122,147,173,209,217,234,261,270,285],"set":[13,27,40,287],"of":[14,28,41,69,119,137,159,184,211,238,256,288],"classes":[15,85,149],"whose":[16],"distinction":[17],"might":[18],"be":[19,33,87,95,151,176,202],"useful":[20],"for":[21,56,65,165,208,232,240],"domain":[23,123,128,255,266],"expert,":[24],"and":[25,83,115,163,228,245,251],"classifications":[29],"that":[30,77,172,269,276],"can":[31,175,201],"actually":[32],"distinguished":[34],"by":[35,178,219,265],"data.":[37],"Often":[38],"a":[39,116,127,221,230],"labels":[42,61,79],"is":[43,161],"defined":[44],"with":[45],"some":[46,84],"initial":[47],"intuition":[48],"but":[49,72],"these":[50,78],"not":[52,81],"best":[54,88],"match":[55],"task.":[58],"For":[59,260],"example,":[60],"have":[62],"been":[63,75],"assigned":[64],"land":[66,257,281],"cover":[67,258,282],"Earth":[71],"it":[73,180],"has":[74],"suspected":[76],"ideal":[82],"may":[86],"split":[89],"into":[90],"subclasses":[91],"whereas":[92],"others":[93],"should":[94,150],"merged.":[96],"This":[97,157],"paper":[98],"formalizes":[99],"this":[100],"problem":[101,174,210],"using":[102],"three":[103],"ingredients:":[104],"existing":[106],"class":[107,212,274],"labels,":[108],"underlying":[110],"separability":[111],"in":[112],"data,":[114],"special":[117],"type":[118,158],"input":[120,160],"from":[121,204],"expert.":[124],"We":[125,169,214,243],"require":[126],"expert":[129],"to":[130,145,167,206,223,226,280],"specify":[131],"an":[132,182,263],"L":[133,135,148],"\u00d7":[134],"matrix":[136],"pairwise":[138],"probabilistic":[139,186],"constraints":[140],"expressing":[141],"their":[142],"beliefs":[143],"as":[144,181],"whether":[146],"kept":[152],"separate,":[153],"merged,":[154],"or":[155],"split.":[156],"intuitive":[162],"easy":[164],"experts":[166,267],"supply.":[168],"then":[170],"show":[171],"solved":[177],"casting":[179],"instance":[183],"penalized":[185],"clustering":[187],"(PPC).":[188],"Our":[189],"method,":[190],"Class-Level":[191],"PPC":[192,195],"(CPPC)":[193],"extends":[194],"showing":[196],"how":[197],"its":[198],"time":[199],"complexity":[200,236],"reduced":[203],"O(N2)":[205],"O(NL)":[207],"re-definition.":[213],"further":[215],"extend":[216],"algorithm":[218,271],"presenting":[220],"heuristic":[222],"measure":[224],"adherence":[225],"constraints,":[227],"providing":[229],"criterion":[231],"determining":[233],"model":[235],"(number":[237],"classes)":[239],"constraint-based":[241],"clustering.":[242],"demonstrate":[244],"evaluate":[246],"CPPC":[247],"on":[248,252],"artificial":[249],"data":[250],"our":[253],"motivating":[254],"classification.":[259],"latter,":[262],"evaluation":[264],"shows":[268],"discovers":[272],"novel":[273],"definitions":[275],"better":[278],"suited":[279],"than":[284],"original":[286],"labels.":[289]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}