{"id":"https://openalex.org/W2793385194","doi":"https://doi.org/10.1109/tkde.2018.2808532","title":"Unsupervised Coupled Metric Similarity for Non-IID Categorical Data","display_name":"Unsupervised Coupled Metric Similarity for Non-IID Categorical Data","publication_year":2018,"publication_date":"2018-02-22","ids":{"openalex":"https://openalex.org/W2793385194","doi":"https://doi.org/10.1109/tkde.2018.2808532","mag":"2793385194"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2018.2808532","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2018.2808532","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"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 Knowledge and Data Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/10453/131610","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Songlei Jian","orcid":"https://orcid.org/0000-0001-5760-6431"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Songlei Jian","raw_affiliation_strings":["Advanced Analytics Institute, University of Technology Sydney, Broadway, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0001-5760-6431","affiliations":[{"raw_affiliation_string":"Advanced Analytics Institute, University of Technology Sydney, Broadway, NSW, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000798681","display_name":"Longbing Cao","orcid":"https://orcid.org/0000-0003-1562-9429"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Longbing Cao","raw_affiliation_strings":["Advanced Analytics Institute, University of Technology Sydney, Broadway, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0003-1562-9429","affiliations":[{"raw_affiliation_string":"Advanced Analytics Institute, University of Technology Sydney, Broadway, NSW, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100625354","display_name":"Kai L\u00fc","orcid":"https://orcid.org/0000-0002-6378-7002"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kai Lu","raw_affiliation_strings":["Laboratory of Science and Technology on Parallel and Distributed Processing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratory of Science and Technology on Parallel and Distributed Processing","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012620879","display_name":"Hang Gao","orcid":"https://orcid.org/0000-0002-1163-5533"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hang Gao","raw_affiliation_strings":["Laboratory of Science and Technology on Parallel and Distributed Processing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratory of Science and Technology on Parallel and Distributed Processing","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.7845,"has_fulltext":false,"cited_by_count":41,"citation_normalized_percentile":{"value":0.92377763,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"30","issue":"9","first_page":"1810","last_page":"1823"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9977999925613403,"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":0.9977999925613403,"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":0.9965000152587891,"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/T10689","display_name":"Remote-Sensing Image Classification","score":0.9925000071525574,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.8059614300727844},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6843715310096741},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6783433556556702},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6666532158851624},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6658248901367188},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5425357222557068},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48726239800453186},{"id":"https://openalex.org/keywords/spectral-clustering","display_name":"Spectral clustering","score":0.4814383387565613},{"id":"https://openalex.org/keywords/independent-and-identically-distributed-random-variables","display_name":"Independent and identically distributed random variables","score":0.4735742509365082},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4532013535499573},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4524475634098053},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.44753268361091614},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4453158676624298},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36959922313690186},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24278759956359863},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.1319284737110138},{"id":"https://openalex.org/keywords/random-variable","display_name":"Random variable","score":0.10954129695892334},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09825530648231506}],"concepts":[{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.8059614300727844},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6843715310096741},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6783433556556702},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6666532158851624},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6658248901367188},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5425357222557068},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48726239800453186},{"id":"https://openalex.org/C105611402","wikidata":"https://www.wikidata.org/wiki/Q2976589","display_name":"Spectral clustering","level":3,"score":0.4814383387565613},{"id":"https://openalex.org/C141513077","wikidata":"https://www.wikidata.org/wiki/Q378542","display_name":"Independent and identically distributed random variables","level":3,"score":0.4735742509365082},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4532013535499573},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4524475634098053},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.44753268361091614},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4453158676624298},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36959922313690186},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24278759956359863},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.1319284737110138},{"id":"https://openalex.org/C122123141","wikidata":"https://www.wikidata.org/wiki/Q176623","display_name":"Random variable","level":2,"score":0.10954129695892334},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09825530648231506},{"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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tkde.2018.2808532","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2018.2808532","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"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 Knowledge and Data Engineering","raw_type":"journal-article"},{"id":"pmh:oai:opus.lib.uts.edu.au:10453/131610","is_oa":true,"landing_page_url":"http://hdl.handle.net/10453/131610","pdf_url":null,"source":{"id":"https://openalex.org/S4306401357","display_name":"UTS ePRESS (University of Technology Sydney)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114017466","host_organization_name":"University of Technology Sydney","host_organization_lineage":["https://openalex.org/I114017466"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Journal Article"}],"best_oa_location":{"id":"pmh:oai:opus.lib.uts.edu.au:10453/131610","is_oa":true,"landing_page_url":"http://hdl.handle.net/10453/131610","pdf_url":null,"source":{"id":"https://openalex.org/S4306401357","display_name":"UTS ePRESS (University of Technology Sydney)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114017466","host_organization_name":"University of Technology Sydney","host_organization_lineage":["https://openalex.org/I114017466"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Journal Article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1496381093","display_name":null,"funder_award_id":"61402492","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G1604406238","display_name":null,"funder_award_id":"2012AA010901","funder_id":"https://openalex.org/F4320335773","funder_display_name":"National High-tech Research and Development Program"},{"id":"https://openalex.org/G2451276260","display_name":null,"funder_award_id":"201603170310","funder_id":"https://openalex.org/F4320322725","funder_display_name":"China Scholarship Council"},{"id":"https://openalex.org/G4188329420","display_name":null,"funder_award_id":"2012AA01A301","funder_id":"https://openalex.org/F4320335773","funder_display_name":"National High-tech Research and Development Program"},{"id":"https://openalex.org/G6387411851","display_name":null,"funder_award_id":"61402486","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7828616416","display_name":null,"funder_award_id":"61379146","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8784413278","display_name":"Modelling and discovering complex interaction relations hidden in group behaviours in businesses, online and social communities","funder_award_id":"DP130102691","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"},{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"},{"id":"https://openalex.org/F4320334924","display_name":"Program for New Century Excellent Talents in University","ror":"https://ror.org/01mv9t934"},{"id":"https://openalex.org/F4320335773","display_name":"National High-tech Research and Development Program","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":69,"referenced_works":["https://openalex.org/W839185196","https://openalex.org/W851208606","https://openalex.org/W872425053","https://openalex.org/W1505823450","https://openalex.org/W1532499126","https://openalex.org/W1549853718","https://openalex.org/W1562135275","https://openalex.org/W1578182119","https://openalex.org/W1594924988","https://openalex.org/W1611112381","https://openalex.org/W1628307106","https://openalex.org/W1692149637","https://openalex.org/W1892947258","https://openalex.org/W1903798548","https://openalex.org/W1972935639","https://openalex.org/W1973309569","https://openalex.org/W1985032507","https://openalex.org/W1990643970","https://openalex.org/W2003048487","https://openalex.org/W2009278541","https://openalex.org/W2013619732","https://openalex.org/W2013950458","https://openalex.org/W2014418634","https://openalex.org/W2021440127","https://openalex.org/W2029064186","https://openalex.org/W2054227223","https://openalex.org/W2064679571","https://openalex.org/W2070812954","https://openalex.org/W2079471494","https://openalex.org/W2080515890","https://openalex.org/W2081825452","https://openalex.org/W2085487226","https://openalex.org/W2096612692","https://openalex.org/W2097998348","https://openalex.org/W2100799972","https://openalex.org/W2105896409","https://openalex.org/W2108782127","https://openalex.org/W2113207826","https://openalex.org/W2113586398","https://openalex.org/W2115477592","https://openalex.org/W2120435692","https://openalex.org/W2132914434","https://openalex.org/W2133288557","https://openalex.org/W2144211451","https://openalex.org/W2148706548","https://openalex.org/W2149230623","https://openalex.org/W2163952039","https://openalex.org/W2171832470","https://openalex.org/W2227943658","https://openalex.org/W2297283352","https://openalex.org/W2338257905","https://openalex.org/W2604915546","https://openalex.org/W2963011376","https://openalex.org/W2999729612","https://openalex.org/W3000384245","https://openalex.org/W3097993951","https://openalex.org/W3201248216","https://openalex.org/W4242221364","https://openalex.org/W4245451182","https://openalex.org/W4289236186","https://openalex.org/W6623524618","https://openalex.org/W6631637103","https://openalex.org/W6636447180","https://openalex.org/W6637499153","https://openalex.org/W6639881474","https://openalex.org/W6674385629","https://openalex.org/W6674470414","https://openalex.org/W6735751019","https://openalex.org/W6801309599"],"related_works":["https://openalex.org/W2495338271","https://openalex.org/W2734734306","https://openalex.org/W1560498978","https://openalex.org/W4312820490","https://openalex.org/W2511442670","https://openalex.org/W3196155444","https://openalex.org/W1457719682","https://openalex.org/W2768893657","https://openalex.org/W2020738241","https://openalex.org/W2568490484"],"abstract_inverted_index":{"Appropriate":[0],"similarity":[1,17,38,126,154],"measures":[2,127,155],"always":[3],"play":[4],"a":[5,54],"critical":[6],"role":[7],"in":[8,76,88],"data":[9,20,42,148],"analytics,":[10],"learning,":[11],"and":[12,29,47,82,85,100,102,118,121,136,146],"processing.":[13],"Measuring":[14],"the":[15,37,67,74,140],"intrinsic":[16,79],"of":[18,40,78,143],"categorical":[19,41,89],"for":[21,36,61],"unsupervised":[22,62],"learning":[23,63],"has":[24,33],"not":[25,45,130],"been":[26,34],"substantially":[27],"addressed,":[28],"even":[30],"less":[31],"effort":[32],"made":[35],"analysis":[39,138],"that":[43,128],"is":[44,59,94,113],"independent":[46,145],"identically":[48],"distributed":[49],"(non-IID).":[50],"In":[51],"this":[52],"work,":[53],"Coupled":[55],"Metric":[56],"Similarity":[57],"(CMS)":[58],"defined":[60],"which":[64,150],"flexibly":[65,105],"captures":[66],"value-to-attribute-to-object":[68],"heterogeneous":[69,80],"coupling":[70],"relationships.":[71],"CMS":[72,92,103,112,141],"learns":[73],"similarities":[75],"terms":[77],"intra-":[81],"inter-attribute":[83],"couplings":[84,87],"attribute-to-object":[86],"data.":[90,111],"The":[91,133],"validity":[93],"guaranteed":[95],"by":[96],"satisfying":[97],"metric":[98],"properties":[99],"conditions,":[101],"can":[104],"adapt":[106],"to":[107,109],"IID":[108],"non-IID":[110],"incorporated":[114],"into":[115],"spectral":[116],"clustering":[117,120],"k-modes":[119],"compared":[122],"with":[123],"relevant":[124],"state-of-the-art":[125],"are":[129],"necessarily":[131],"metrics.":[132],"experimental":[134],"results":[135],"theoretical":[137],"show":[139],"effectiveness":[142],"capturing":[144],"coupled":[147],"characteristics,":[149],"significantly":[151],"outperforms":[152],"other":[153],"on":[156],"most":[157],"datasets.":[158]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}