{"id":"https://openalex.org/W1991893201","doi":"https://doi.org/10.1145/2623330.2623652","title":"Relevant overlapping subspace clusters on categorical data","display_name":"Relevant overlapping subspace clusters on categorical data","publication_year":2014,"publication_date":"2014-08-22","ids":{"openalex":"https://openalex.org/W1991893201","doi":"https://doi.org/10.1145/2623330.2623652","mag":"1991893201"},"language":"en","primary_location":{"id":"doi:10.1145/2623330.2623652","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2623330.2623652","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://push-zb.helmholtz-muenchen.de/frontdoor.php?source_opus=43095","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108459503","display_name":"Xiao He","orcid":"https://orcid.org/0000-0002-3000-0795"},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Xiao He","raw_affiliation_strings":["University of Munich, Munich, Germany","University of Munich, Munich, GERMANY#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I8204097"]},{"raw_affiliation_string":"University of Munich, Munich, GERMANY#TAB#","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102940907","display_name":"Jing Feng","orcid":"https://orcid.org/0000-0002-7425-2994"},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jing Feng","raw_affiliation_strings":["University of Munich, Munich, Germany","University of Munich, Munich, GERMANY#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I8204097"]},{"raw_affiliation_string":"University of Munich, Munich, GERMANY#TAB#","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009805750","display_name":"Bettina Konte","orcid":"https://orcid.org/0000-0001-5287-308X"},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bettina Konte","raw_affiliation_strings":["University of Munich, Munich, Germany","University of Munich, Munich, GERMANY#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I8204097"]},{"raw_affiliation_string":"University of Munich, Munich, GERMANY#TAB#","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Son T. Mai","orcid":null},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Son T. Mai","raw_affiliation_strings":["University of Munich, Munich, Germany","University of Munich, Munich, GERMANY#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I8204097"]},{"raw_affiliation_string":"University of Munich, Munich, GERMANY#TAB#","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009516958","display_name":"Claudia Plant","orcid":"https://orcid.org/0000-0001-5274-8123"},"institutions":[{"id":"https://openalex.org/I3018134672","display_name":"Helmholtz Zentrum M\u00fcnchen","ror":"https://ror.org/00cfam450","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I3018134672"]},{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Claudia Plant","raw_affiliation_strings":["Helmholtz Zentrum M\u00fcnchen, Technische Universit\u00e4t M\u00fcnchen, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Helmholtz Zentrum M\u00fcnchen, Technische Universit\u00e4t M\u00fcnchen, Munich, Germany","institution_ids":["https://openalex.org/I3018134672","https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"213","last_page":"222"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T11106","display_name":"Data Management and Algorithms","score":0.9958999752998352,"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/T10064","display_name":"Complex Network Analysis Techniques","score":0.9908000230789185,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/linear-subspace","display_name":"Linear subspace","score":0.8202746510505676},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.784315824508667},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.7609462141990662},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7068279385566711},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6949657797813416},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.6299028992652893},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.60749351978302},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5180568695068359},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4469960927963257},{"id":"https://openalex.org/keywords/clustering-high-dimensional-data","display_name":"Clustering high-dimensional data","score":0.4272249639034271},{"id":"https://openalex.org/keywords/data-redundancy","display_name":"Data redundancy","score":0.42212820053100586},{"id":"https://openalex.org/keywords/data-point","display_name":"Data point","score":0.4175664782524109},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39484497904777527},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24758267402648926},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.19927313923835754},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.06618127226829529}],"concepts":[{"id":"https://openalex.org/C12362212","wikidata":"https://www.wikidata.org/wiki/Q728435","display_name":"Linear subspace","level":2,"score":0.8202746510505676},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.784315824508667},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.7609462141990662},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7068279385566711},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6949657797813416},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.6299028992652893},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.60749351978302},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5180568695068359},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4469960927963257},{"id":"https://openalex.org/C184509293","wikidata":"https://www.wikidata.org/wiki/Q5136711","display_name":"Clustering high-dimensional data","level":3,"score":0.4272249639034271},{"id":"https://openalex.org/C7545210","wikidata":"https://www.wikidata.org/wiki/Q838123","display_name":"Data redundancy","level":2,"score":0.42212820053100586},{"id":"https://openalex.org/C21080849","wikidata":"https://www.wikidata.org/wiki/Q13611879","display_name":"Data point","level":2,"score":0.4175664782524109},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39484497904777527},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24758267402648926},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.19927313923835754},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.06618127226829529},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2623330.2623652","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2623330.2623652","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},{"id":"pmh:oai:opus-zb.helmholtz-muenchen.de:43095","is_oa":true,"landing_page_url":"https://push-zb.helmholtz-muenchen.de/frontdoor.php?source_opus=43095","pdf_url":null,"source":{"id":"https://openalex.org/S4377196115","display_name":"Site cant be reached","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"In: Proceedings (20th ACM SIGKDD international conference on Knowledge discovery and data mining, 24-27 August 2014, New York, NY, USA). New York, NY, USA: ACM, 2014. 213-222","raw_type":"conferenceObject"}],"best_oa_location":{"id":"pmh:oai:opus-zb.helmholtz-muenchen.de:43095","is_oa":true,"landing_page_url":"https://push-zb.helmholtz-muenchen.de/frontdoor.php?source_opus=43095","pdf_url":null,"source":{"id":"https://openalex.org/S4377196115","display_name":"Site cant be reached","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"In: Proceedings (20th ACM SIGKDD international conference on Knowledge discovery and data mining, 24-27 August 2014, New York, NY, USA). New York, NY, USA: ACM, 2014. 213-222","raw_type":"conferenceObject"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W31165685","https://openalex.org/W1481232215","https://openalex.org/W1560541823","https://openalex.org/W1562135275","https://openalex.org/W1972132022","https://openalex.org/W1977496278","https://openalex.org/W1984253569","https://openalex.org/W2011039300","https://openalex.org/W2034230784","https://openalex.org/W2057712948","https://openalex.org/W2059453880","https://openalex.org/W2064686951","https://openalex.org/W2079361215","https://openalex.org/W2089055054","https://openalex.org/W2108120750","https://openalex.org/W2111317215","https://openalex.org/W2122943553","https://openalex.org/W2124066753","https://openalex.org/W2140439590","https://openalex.org/W2144767994","https://openalex.org/W2146442966","https://openalex.org/W2148744937","https://openalex.org/W2151979140","https://openalex.org/W2163067442","https://openalex.org/W2476096155","https://openalex.org/W2886661658","https://openalex.org/W4252115301"],"related_works":["https://openalex.org/W227974271","https://openalex.org/W2465328940","https://openalex.org/W2605086803","https://openalex.org/W2968737478","https://openalex.org/W2103268563","https://openalex.org/W88288160","https://openalex.org/W2761926807","https://openalex.org/W2330313492","https://openalex.org/W2533990316","https://openalex.org/W2952300832"],"abstract_inverted_index":{"Clustering":[0],"categorical":[1,148],"data":[2,51,85,149],"poses":[3],"some":[4],"unique":[5],"challenges:":[6],"Due":[7],"to":[8,31,38,45,115,135,143,162,172],"missing":[9],"order":[10],"and":[11,60,124,168,184,201],"spacing":[12],"among":[13],"the":[14,29,49,82,88,96,117,120,137,193,199],"categories,":[15],"selecting":[16],"a":[17,22,77,130],"suitable":[18],"similarity":[19],"measure":[20],"is":[21,110,140],"difficult":[23,37],"task.":[24],"Many":[25],"existing":[26],"techniques":[27,42],"require":[28],"user":[30],"specify":[32],"input":[33,103],"parameters":[34],"which":[35,150],"are":[36,43],"estimate.":[39],"Moreover,":[40],"many":[41],"limited":[44],"detect":[46,144],"clusters":[47,100,134,146,164,183],"in":[48,153,165,182],"full-dimensional":[50],"space.":[52],"Only":[53],"few":[54],"methods":[55],"exist":[56],"for":[57],"subspace":[58,99,145],"clustering":[59],"they":[61],"produce":[62],"highly":[63],"redundant":[64],"results.":[65],"Therefore,":[66],"we":[67],"propose":[68],"ROCAT":[69,93,127,139,177],"(Relevant":[70],"Overlapping":[71],"Subspace":[72],"Clusters":[73],"on":[74,81,147],"Categorical":[75],"Data),":[76],"novel":[78],"technique":[79],"based":[80],"idea":[83],"of":[84,107,133,203],"compression.":[86],"Following":[87],"Minimum":[89],"Description":[90],"Length":[91],"principle,":[92],"automatically":[94,128],"detects":[95],"most":[97],"relevant":[98],"without":[101],"any":[102],"parameter.":[104],"The":[105],"relevance":[106],"each":[108],"cluster":[109],"validated":[111],"by":[112,186],"its":[113],"contribution":[114],"compress":[116],"data.":[118,138],"Optimizing":[119],"trade-off":[121],"between":[122],"goodness-of-fit":[123],"model":[125],"complexity,":[126],"determines":[129],"meaningful":[131],"number":[132],"represent":[136],"especially":[141],"designed":[142],"may":[151,170],"overlap":[152,188],"objects":[154,158],"and/or":[155],"attributes;":[156],"i.e.":[157],"can":[159],"be":[160],"assigned":[161],"different":[163,166,173],"subspaces":[167,174,185],"attributes":[169],"contribute":[171],"containing":[175],"clusters.":[176],"naturally":[178],"avoids":[179],"undesired":[180],"redundancy":[181],"allowing":[187],"only":[189],"if":[190],"it":[191],"improves":[192],"compression":[194],"rate.":[195],"Extensive":[196],"experiments":[197],"demonstrate":[198],"effectiveness":[200],"efficiency":[202],"our":[204],"approach.":[205]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}