{"id":"https://openalex.org/W4410398663","doi":"https://doi.org/10.1145/3735977","title":"Clustering Categorical Data via Multiple Hypothesis Testing","display_name":"Clustering Categorical Data via Multiple Hypothesis Testing","publication_year":2025,"publication_date":"2025-05-15","ids":{"openalex":"https://openalex.org/W4410398663","doi":"https://doi.org/10.1145/3735977"},"language":"en","primary_location":{"id":"doi:10.1145/3735977","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3735977","pdf_url":null,"source":{"id":"https://openalex.org/S41523882","display_name":"ACM Transactions on Knowledge Discovery from Data","issn_l":"1556-4681","issn":["1556-4681","1556-472X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Knowledge Discovery from Data","raw_type":"journal-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/A5089849427","display_name":"Lianyu Hu","orcid":"https://orcid.org/0000-0001-7470-9395"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lianyu Hu","raw_affiliation_strings":["School of Software, Dalian University of Technology, Dalian, China","School of Software, Dalian University of Technology, China"],"raw_orcid":"https://orcid.org/0000-0001-7470-9395","affiliations":[{"raw_affiliation_string":"School of Software, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]},{"raw_affiliation_string":"School of Software, Dalian University of Technology, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087422170","display_name":"Mudi Jiang","orcid":"https://orcid.org/0000-0001-9474-8375"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mudi Jiang","raw_affiliation_strings":["School of Software, Dalian University of Technology, Dalian, China","School of Software, Dalian University of Technology, China"],"raw_orcid":"https://orcid.org/0000-0001-9474-8375","affiliations":[{"raw_affiliation_string":"School of Software, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]},{"raw_affiliation_string":"School of Software, Dalian University of Technology, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075618278","display_name":"Yan Liu","orcid":"https://orcid.org/0000-0002-1386-812X"},"institutions":[{"id":"https://openalex.org/I4210092944","display_name":"Dalian University","ror":"https://ror.org/00g2ypp58","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210092944"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Liu","raw_affiliation_strings":["School of Software Engineering, Dalian University, Dalian, China","School of Software Engineering, Dalian University, China"],"raw_orcid":"https://orcid.org/0000-0002-1386-812X","affiliations":[{"raw_affiliation_string":"School of Software Engineering, Dalian University, Dalian, China","institution_ids":["https://openalex.org/I4210092944"]},{"raw_affiliation_string":"School of Software Engineering, Dalian University, China","institution_ids":["https://openalex.org/I4210092944"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017426085","display_name":"Quan Zou","orcid":"https://orcid.org/0000-0001-6406-1142"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Quan Zou","raw_affiliation_strings":["Institute of Fundamental and Frontier Sciences, University of Electronic Science and Technology of China, Chengdu, China","Institute of Fundamental and Frontier Sciences, University of Electronic Science and Technology of China, China"],"raw_orcid":"https://orcid.org/0000-0001-6406-1142","affiliations":[{"raw_affiliation_string":"Institute of Fundamental and Frontier Sciences, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"Institute of Fundamental and Frontier Sciences, University of Electronic Science and Technology of China, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009588567","display_name":"Zengyou He","orcid":"https://orcid.org/0000-0001-9526-8816"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zengyou He","raw_affiliation_strings":["School of Software, Dalian University of Technology, Dalian, China","School of Software, Dalian University of Technology, China"],"raw_orcid":"https://orcid.org/0000-0001-9526-8816","affiliations":[{"raw_affiliation_string":"School of Software, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]},{"raw_affiliation_string":"School of Software, Dalian University of Technology, China","institution_ids":["https://openalex.org/I27357992"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5089849427"],"corresponding_institution_ids":["https://openalex.org/I27357992"],"apc_list":null,"apc_paid":null,"fwci":4.3465,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.93838474,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"19","issue":"5","first_page":"1","last_page":"31"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9991000294685364,"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":0.9991000294685364,"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/T10057","display_name":"Face and Expression Recognition","score":0.9926000237464905,"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"}},{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9905999898910522,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/categorical-variable","display_name":"Categorical variable","score":0.7244771718978882},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7162191867828369},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5275064706802368},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5102596282958984},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39517682790756226},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.29062312841415405}],"concepts":[{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.7244771718978882},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7162191867828369},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5275064706802368},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5102596282958984},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39517682790756226},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29062312841415405}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3735977","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3735977","pdf_url":null,"source":{"id":"https://openalex.org/S41523882","display_name":"ACM Transactions on Knowledge Discovery from Data","issn_l":"1556-4681","issn":["1556-4681","1556-472X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Knowledge Discovery from Data","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4254997053","display_name":null,"funder_award_id":"62472064","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":97,"referenced_works":["https://openalex.org/W71228264","https://openalex.org/W317995076","https://openalex.org/W1483330700","https://openalex.org/W1524704912","https://openalex.org/W1535743328","https://openalex.org/W1562135275","https://openalex.org/W1565746575","https://openalex.org/W1570155537","https://openalex.org/W1576534100","https://openalex.org/W1982658582","https://openalex.org/W1984390238","https://openalex.org/W1989688078","https://openalex.org/W1991767154","https://openalex.org/W2002575106","https://openalex.org/W2005934890","https://openalex.org/W2007635740","https://openalex.org/W2008689893","https://openalex.org/W2011430131","https://openalex.org/W2011978385","https://openalex.org/W2014419562","https://openalex.org/W2027241418","https://openalex.org/W2032801341","https://openalex.org/W2040360010","https://openalex.org/W2045668838","https://openalex.org/W2047878524","https://openalex.org/W2057712948","https://openalex.org/W2064686951","https://openalex.org/W2069334182","https://openalex.org/W2072898312","https://openalex.org/W2073308541","https://openalex.org/W2074615058","https://openalex.org/W2079188092","https://openalex.org/W2081684867","https://openalex.org/W2086718322","https://openalex.org/W2086829791","https://openalex.org/W2106678396","https://openalex.org/W2110094288","https://openalex.org/W2116984363","https://openalex.org/W2120887445","https://openalex.org/W2121861830","https://openalex.org/W2121947440","https://openalex.org/W2135748228","https://openalex.org/W2145721327","https://openalex.org/W2149230623","https://openalex.org/W2154532634","https://openalex.org/W2169658215","https://openalex.org/W2171832470","https://openalex.org/W2255394077","https://openalex.org/W2338257905","https://openalex.org/W2353261545","https://openalex.org/W2473552888","https://openalex.org/W2563646325","https://openalex.org/W2568618480","https://openalex.org/W2601530120","https://openalex.org/W2604043882","https://openalex.org/W2604272474","https://openalex.org/W2605641866","https://openalex.org/W2743926534","https://openalex.org/W2793385194","https://openalex.org/W2801677142","https://openalex.org/W2811024573","https://openalex.org/W2888523397","https://openalex.org/W2911984381","https://openalex.org/W2914761779","https://openalex.org/W2914874661","https://openalex.org/W2944000174","https://openalex.org/W2962809812","https://openalex.org/W2964099478","https://openalex.org/W2997546679","https://openalex.org/W3043639995","https://openalex.org/W3043922872","https://openalex.org/W3082282088","https://openalex.org/W3089099140","https://openalex.org/W3104583603","https://openalex.org/W3111795212","https://openalex.org/W3128396846","https://openalex.org/W3157327230","https://openalex.org/W3172701880","https://openalex.org/W3216043206","https://openalex.org/W3216660278","https://openalex.org/W4206504490","https://openalex.org/W4206784936","https://openalex.org/W4223983416","https://openalex.org/W4224313447","https://openalex.org/W4234536190","https://openalex.org/W4235169531","https://openalex.org/W4249589601","https://openalex.org/W4250589301","https://openalex.org/W4285471463","https://openalex.org/W4285605356","https://openalex.org/W4295308409","https://openalex.org/W4403807737","https://openalex.org/W4406086321","https://openalex.org/W4406524282","https://openalex.org/W4406588604","https://openalex.org/W4406892970","https://openalex.org/W6679407316"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4386799044","https://openalex.org/W2773208253","https://openalex.org/W2560646951","https://openalex.org/W4297454206","https://openalex.org/W65104662","https://openalex.org/W1871748041","https://openalex.org/W2362286668"],"abstract_inverted_index":{"Categorical":[0],"data":[1,6,26,37,77,162],"clustering":[2,22,38,78,124,163,179],"is":[3,90,94,126,134,153,189],"a":[4,61,81,114,122,169,178,184],"fundamental":[5],"mining":[7],"problem,":[8,85],"which":[9,129],"has":[10,168],"been":[11],"extensively":[12],"studied":[13],"during":[14],"the":[15,30,43,46,57,75,87,97,130],"past":[16],"decades.":[17],"To":[18],"date,":[19],"many":[20],"effective":[21],"algorithms":[23,39],"for":[24],"categorical":[25,36,65,76,161],"are":[27,110],"available":[28],"in":[29,128,137],"literature.":[31],"However,":[32],"almost":[33],"all":[34,103],"existing":[35],"did":[40],"not":[41],"address":[42],"issue":[44],"of":[45,49,60,63,96,100,155,172,187],"statistical":[47,58,119],"significance":[48,59],"detected":[50],"clusters.":[51,101],"In":[52,70],"particular,":[53],"how":[54],"to":[55,112,159],"assess":[56],"set":[62,186],"non-overlapping":[64],"clusters":[66,188],"still":[67],"remains":[68],"unaddressed.":[69],"this":[71],"article,":[72],"we":[73],"formulate":[74],"problem":[79],"as":[80],"multiple":[82],"hypothesis":[83,89],"testing":[84],"where":[86],"null":[88],"that":[91,150],"each":[92],"attribute":[93],"independent":[95],"given":[98,185],"partition":[99],"Then,":[102],"individual":[104],"\\(p\\)":[105,116,132],"-values":[106],"from":[107],"different":[108],"attributes":[109],"integrated":[111],"obtain":[113],"consensus":[115],"-value":[117,133],"through":[118],"meta-analysis.":[120],"Thereafter,":[121],"significance-based":[123],"algorithm":[125],"proposed":[127],"combined":[131],"efficiently":[135],"optimized":[136],"an":[138],"indirectly":[139],"and":[140,181],"incremental":[141],"manner.":[142],"Experimental":[143],"results":[144],"on":[145],"25":[146],"real-world":[147],"datasets":[148],"demonstrate":[149],"our":[151,166],"method":[152,167],"capable":[154],"achieving":[156],"comparable":[157],"performance":[158],"state-of-the-art":[160],"algorithms.":[164],"Furthermore,":[165],"good":[170],"capability":[171],"determining":[173],"whether":[174,183],"there":[175],"really":[176],"exists":[177],"structure":[180],"assessing":[182],"statistically":[190],"significant.":[191]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}