{"id":"https://openalex.org/W7109009712","doi":"https://doi.org/10.1145/3769772","title":"Categorical Data Clustering via Value Order Estimated Distance Metric Learning","display_name":"Categorical Data Clustering via Value Order Estimated Distance Metric Learning","publication_year":2025,"publication_date":"2025-12-04","ids":{"openalex":"https://openalex.org/W7109009712","doi":"https://doi.org/10.1145/3769772"},"language":"en","primary_location":{"id":"doi:10.1145/3769772","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3769772","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3769772","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yiqun Zhang","orcid":"https://orcid.org/0000-0002-0328-987X"},"institutions":[{"id":"https://openalex.org/I141568987","display_name":"Hong Kong Baptist University","ror":"https://ror.org/0145fw131","country_code":"HK","type":"education","lineage":["https://openalex.org/I141568987"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Yiqun Zhang","raw_affiliation_strings":["School of Computer Science and Technology, Guangdong University of Technology, Guangzhou, China and Department of Computer Science, Hong Kong Baptist University, Kowloon Tong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Guangdong University of Technology, Guangzhou, China and Department of Computer Science, Hong Kong Baptist University, Kowloon Tong, Hong Kong","institution_ids":["https://openalex.org/I141568987"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Mingjie Zhao","orcid":"https://orcid.org/0009-0009-5517-4845"},"institutions":[{"id":"https://openalex.org/I141568987","display_name":"Hong Kong Baptist University","ror":"https://ror.org/0145fw131","country_code":"HK","type":"education","lineage":["https://openalex.org/I141568987"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Mingjie Zhao","raw_affiliation_strings":["Department of Computer Science, Hong Kong Baptist University, Kowloon Tong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Hong Kong Baptist University, Kowloon Tong, Hong Kong","institution_ids":["https://openalex.org/I141568987"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hong Jia","orcid":"https://orcid.org/0000-0001-9352-2366"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Jia","raw_affiliation_strings":["College of Electronics and Information Engineering, Shenzhen University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"College of Electronics and Information Engineering, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Mengke Li","orcid":"https://orcid.org/0000-0002-9433-9683"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengke Li","raw_affiliation_strings":["College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yang Lu","orcid":"https://orcid.org/0000-0002-3497-9611"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Lu","raw_affiliation_strings":["School of Informatics, Xiamen University, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"School of Informatics, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"last","author":{"id":null,"display_name":"Yiu-ming Cheung","orcid":"https://orcid.org/0000-0001-7629-4648"},"institutions":[{"id":"https://openalex.org/I141568987","display_name":"Hong Kong Baptist University","ror":"https://ror.org/0145fw131","country_code":"HK","type":"education","lineage":["https://openalex.org/I141568987"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yiu-ming Cheung","raw_affiliation_strings":["Department of Computer Science, Hong Kong Baptist University, Kowloon Tong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Hong Kong Baptist University, Kowloon Tong, Hong Kong","institution_ids":["https://openalex.org/I141568987"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I141568987"],"apc_list":null,"apc_paid":null,"fwci":2.3568,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.93250342,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"3","issue":"6","first_page":"1","last_page":"24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.5486999750137329,"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":0.5486999750137329,"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":0.13439999520778656,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.05310000106692314,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.7580000162124634},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6811000108718872},{"id":"https://openalex.org/keywords/euclidean-distance","display_name":"Euclidean distance","score":0.6521000266075134},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5870000123977661},{"id":"https://openalex.org/keywords/distance-measures","display_name":"Distance measures","score":0.4422999918460846},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4147000014781952},{"id":"https://openalex.org/keywords/euclidean-space","display_name":"Euclidean space","score":0.3946000039577484},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3847000002861023},{"id":"https://openalex.org/keywords/metric-space","display_name":"Metric space","score":0.33739998936653137}],"concepts":[{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.7580000162124634},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6811000108718872},{"id":"https://openalex.org/C120174047","wikidata":"https://www.wikidata.org/wiki/Q847073","display_name":"Euclidean distance","level":2,"score":0.6521000266075134},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5870000123977661},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5246000289916992},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.47110000252723694},{"id":"https://openalex.org/C2639959","wikidata":"https://www.wikidata.org/wiki/Q1344778","display_name":"Distance measures","level":2,"score":0.4422999918460846},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4194999933242798},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.41609999537467957},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4147000014781952},{"id":"https://openalex.org/C186450821","wikidata":"https://www.wikidata.org/wiki/Q17295","display_name":"Euclidean space","level":2,"score":0.3946000039577484},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3847000002861023},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3515999913215637},{"id":"https://openalex.org/C198043062","wikidata":"https://www.wikidata.org/wiki/Q180953","display_name":"Metric space","level":2,"score":0.33739998936653137},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.32519999146461487},{"id":"https://openalex.org/C100279318","wikidata":"https://www.wikidata.org/wiki/Q467440","display_name":"Sample space","level":2,"score":0.31060001254081726},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.3093999922275543},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.3050999939441681},{"id":"https://openalex.org/C111208986","wikidata":"https://www.wikidata.org/wiki/Q901698","display_name":"Distance matrix","level":2,"score":0.3000999987125397},{"id":"https://openalex.org/C5349765","wikidata":"https://www.wikidata.org/wiki/Q5282866","display_name":"Distance matrices in phylogeny","level":2,"score":0.2892000079154968},{"id":"https://openalex.org/C149073432","wikidata":"https://www.wikidata.org/wiki/Q4960382","display_name":"Bregman divergence","level":2,"score":0.2815999984741211},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.2797999978065491},{"id":"https://openalex.org/C85461838","wikidata":"https://www.wikidata.org/wiki/Q7100785","display_name":"Ordinal data","level":2,"score":0.27950000762939453},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C184509293","wikidata":"https://www.wikidata.org/wiki/Q5136711","display_name":"Clustering high-dimensional data","level":3,"score":0.2655999958515167},{"id":"https://openalex.org/C21080849","wikidata":"https://www.wikidata.org/wiki/Q13611879","display_name":"Data point","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C129782007","wikidata":"https://www.wikidata.org/wiki/Q162886","display_name":"Euclidean geometry","level":2,"score":0.2547999918460846}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3769772","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3769772","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3769772","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3769772","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1762107681","display_name":null,"funder_award_id":"2025A1515011293","funder_id":"https://openalex.org/F4320321921","funder_display_name":"Natural Science Foundation of Guangdong Province"},{"id":"https://openalex.org/G3782241773","display_name":null,"funder_award_id":"RCBS20231211090659101","funder_id":"https://openalex.org/F4320336569","funder_display_name":"Shenzhen Science and Technology Innovation Program"},{"id":"https://openalex.org/G625985749","display_name":null,"funder_award_id":"2024J09001","funder_id":"https://openalex.org/F4320321878","funder_display_name":"Natural Science Foundation of Fujian Province"},{"id":"https://openalex.org/G8417947499","display_name":null,"funder_award_id":"62476063, 62376233, 61806131, 62306181","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"},{"id":"https://openalex.org/F4320321878","display_name":"Natural Science Foundation of Fujian Province","ror":null},{"id":"https://openalex.org/F4320321921","display_name":"Natural Science Foundation of Guangdong Province","ror":null},{"id":"https://openalex.org/F4320336569","display_name":"Shenzhen Science and Technology Innovation Program","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2010140249","https://openalex.org/W2033403400","https://openalex.org/W2040138869","https://openalex.org/W2041674806","https://openalex.org/W2047878524","https://openalex.org/W2064535593","https://openalex.org/W2071715137","https://openalex.org/W2105431676","https://openalex.org/W2132149726","https://openalex.org/W2144549472","https://openalex.org/W2149230623","https://openalex.org/W2156483112","https://openalex.org/W2338257905","https://openalex.org/W2473552888","https://openalex.org/W2743926534","https://openalex.org/W2793385194","https://openalex.org/W2811024573","https://openalex.org/W2925162041","https://openalex.org/W3017786722","https://openalex.org/W3091167051","https://openalex.org/W4223983416","https://openalex.org/W4285049621","https://openalex.org/W4295308409","https://openalex.org/W4407281616","https://openalex.org/W4407357336","https://openalex.org/W4410536382","https://openalex.org/W4411403189"],"related_works":[],"abstract_inverted_index":{"Clustering":[0],"is":[1,47,111,124,214],"a":[2,29,64,88,119,140],"popular":[3],"machine":[4],"learning":[5,69,78,122,134,149],"technique":[6],"for":[7],"data":[8,26,46],"mining":[9],"that":[10,92],"can":[11,54],"process":[12],"and":[13,50,83,105,130,139,151,160,172,188],"analyze":[14],"datasets":[15],"to":[16,71,91,126,145],"automatically":[17],"reveal":[18],"sample":[19],"distribution":[20,43],"patterns.":[21],"Since":[22,97],"the":[23,35,42,94,107,114,146,152,157,163,177,184,190,205,208],"ubiquitous":[24],"categorical":[25,45,74,101,171,192],"naturally":[27],"lack":[28],"well-defined":[30],"metric":[31,68,110,133,181],"space":[32,38],"such":[33],"as":[34],"Euclidean":[36,161],"distance":[37,67,86,109,132,159,180],"of":[39,44,93,116,142,156,186,207],"numerical":[40,95],"data,":[41],"usually":[48],"under-represented,":[49],"thus":[51],"valuable":[52],"information":[53],"be":[55],"easily":[56],"twisted":[57],"in":[58,87,113],"clustering.":[59,117],"This":[60],"paper,":[61],"therefore,":[62],"introduces":[63],"novel":[65],"order":[66,81,108,131,148,158,179],"approach":[70],"intuitively":[72],"represent":[73],"attribute":[75],"values":[76,102],"by":[77],"their":[79,85],"optimal":[80],"relationship":[82],"quantifying":[84],"line":[89],"similar":[90],"attributes.":[96],"subjectively":[98],"created":[99],"qualitative":[100],"involve":[103],"ambiguity":[104],"fuzziness,":[106],"learned":[112,178],"context":[115],"Accordingly,":[118],"new":[120],"joint":[121],"paradigm":[123],"developed":[125],"alternatively":[127],"perform":[128],"clustering":[129,168],"with":[135,195],"low":[136],"time":[137],"complexity":[138],"guarantee":[141],"convergence.":[143],"Due":[144],"clustering-friendly":[147],"mechanism":[150],"homogeneous":[153],"ordinal":[154],"nature":[155],"distance,":[162],"proposed":[164,209],"method":[165],"achieves":[166],"superior":[167],"accuracy":[169],"on":[170],"mixed":[173],"datasets.":[174],"More":[175],"importantly,":[176],"greatly":[182],"reduces":[183],"difficulty":[185],"understanding":[187],"managing":[189],"non-intuitive":[191],"data.":[193],"Experiments":[194],"ablation":[196],"studies,":[197,201],"significance":[198],"tests,":[199],"case":[200],"etc.,":[202],"have":[203],"validated":[204],"efficacy":[206],"method.":[210],"The":[211],"source":[212],"code":[213],"available":[215],"at":[216],"https://github.com/csmjzhao/OCL_Source_Code.":[217]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-12-06T00:00:00"}