{"id":"https://openalex.org/W4411403189","doi":"https://doi.org/10.1145/3725366","title":"TableDC: Deep Clustering for Tabular Data","display_name":"TableDC: Deep Clustering for Tabular Data","publication_year":2025,"publication_date":"2025-06-17","ids":{"openalex":"https://openalex.org/W4411403189","doi":"https://doi.org/10.1145/3725366"},"language":"en","primary_location":{"id":"doi:10.1145/3725366","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3725366","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/10.1145/3725366","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070901131","display_name":"Hafiz Tayyab Rauf","orcid":"https://orcid.org/0000-0002-1515-3187"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Hafiz Tayyab Rauf","raw_affiliation_strings":["Department of Computer Science, University of Manchester, Manchester, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-1515-3187","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Manchester, Manchester, United Kingdom","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Andr\u00e9 Freitas","orcid":"https://orcid.org/0000-0002-4430-4837"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]},{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH","GB"],"is_corresponding":false,"raw_author_name":"Andr\u00e9 Freitas","raw_affiliation_strings":["Department of Computer Science, University of Manchester, Manchester, United Kingdom and IDIAP Research Institute, Martigny, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-4430-4837","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Manchester, Manchester, United Kingdom and IDIAP Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I28407311","https://openalex.org/I7495430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066619159","display_name":"Norman W. Paton","orcid":"https://orcid.org/0000-0003-2008-6617"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Norman William Paton","raw_affiliation_strings":["Department of Computer Science, University of Manchester, Manchester, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0003-2008-6617","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Manchester, Manchester, United Kingdom","institution_ids":["https://openalex.org/I28407311"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2699,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.84282598,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"3","issue":"3","first_page":"1","last_page":"28"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9983999729156494,"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":0.9983999729156494,"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/T11819","display_name":"Data-Driven Disease Surveillance","score":0.9947999715805054,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9921000003814697,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7417944073677063},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7073389291763306},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5914540886878967},{"id":"https://openalex.org/keywords/clustering-high-dimensional-data","display_name":"Clustering high-dimensional data","score":0.4626100957393646},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4404878318309784},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43681958317756653},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4251408874988556},{"id":"https://openalex.org/keywords/data-stream-clustering","display_name":"Data stream clustering","score":0.4142264723777771},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.40822333097457886},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.34202706813812256},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.15459796786308289}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7417944073677063},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7073389291763306},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5914540886878967},{"id":"https://openalex.org/C184509293","wikidata":"https://www.wikidata.org/wiki/Q5136711","display_name":"Clustering high-dimensional data","level":3,"score":0.4626100957393646},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4404878318309784},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43681958317756653},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4251408874988556},{"id":"https://openalex.org/C193143536","wikidata":"https://www.wikidata.org/wiki/Q5227360","display_name":"Data stream clustering","level":5,"score":0.4142264723777771},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.40822333097457886},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.34202706813812256},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.15459796786308289}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3725366","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3725366","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"},{"id":"pmh:oai:pure.atira.dk:publications/4daa0e19-8c1e-4351-b23b-de7e31ab5d13","is_oa":true,"landing_page_url":"https://research.manchester.ac.uk/en/publications/4daa0e19-8c1e-4351-b23b-de7e31ab5d13","pdf_url":"https://pure.manchester.ac.uk/ws/files/361658222/2405.17723v1.pdf","source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"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":"Rauf, H T, Freitas, A & Paton, N 2025, TableDC : Deep Clustering for Tabular Data. in Proceedings of the ACM on Management of Data. 3 edn, vol. 3, 229, Association for Computing Machinery, pp. 1-28. https://doi.org/10.1145/3725366","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.1145/3725366","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3725366","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":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":76,"referenced_works":["https://openalex.org/W1976437052","https://openalex.org/W1977556410","https://openalex.org/W2004539934","https://openalex.org/W2033403400","https://openalex.org/W2095897464","https://openalex.org/W2117539524","https://openalex.org/W2129793592","https://openalex.org/W2131681506","https://openalex.org/W2148524305","https://openalex.org/W2150102617","https://openalex.org/W2162363099","https://openalex.org/W2165612380","https://openalex.org/W2404301904","https://openalex.org/W2560674852","https://openalex.org/W2604190938","https://openalex.org/W2604647163","https://openalex.org/W2608862709","https://openalex.org/W2626982577","https://openalex.org/W2730106296","https://openalex.org/W2741943936","https://openalex.org/W2798664493","https://openalex.org/W2891177506","https://openalex.org/W2891515342","https://openalex.org/W2963761396","https://openalex.org/W2971681342","https://openalex.org/W2974662081","https://openalex.org/W2981852735","https://openalex.org/W2986063762","https://openalex.org/W2994560339","https://openalex.org/W3004300812","https://openalex.org/W3004946360","https://openalex.org/W3011807731","https://openalex.org/W3013008430","https://openalex.org/W3014616325","https://openalex.org/W3014705052","https://openalex.org/W3024644820","https://openalex.org/W3029269967","https://openalex.org/W3029701880","https://openalex.org/W3092962901","https://openalex.org/W3099768174","https://openalex.org/W3101709902","https://openalex.org/W3103177583","https://openalex.org/W3106020963","https://openalex.org/W3123375411","https://openalex.org/W3137513727","https://openalex.org/W3146259567","https://openalex.org/W3173294575","https://openalex.org/W3173874612","https://openalex.org/W3216718110","https://openalex.org/W4206908526","https://openalex.org/W4226219101","https://openalex.org/W4235169531","https://openalex.org/W4281971614","https://openalex.org/W4283011496","https://openalex.org/W4285606887","https://openalex.org/W4285610178","https://openalex.org/W4288089799","https://openalex.org/W4290927762","https://openalex.org/W4311906819","https://openalex.org/W4312258136","https://openalex.org/W4312459443","https://openalex.org/W4312834202","https://openalex.org/W4375928372","https://openalex.org/W4382239329","https://openalex.org/W4382466430","https://openalex.org/W4383051975","https://openalex.org/W4383199654","https://openalex.org/W4385764280","https://openalex.org/W4385767379","https://openalex.org/W4385767705","https://openalex.org/W4385767799","https://openalex.org/W4386075537","https://openalex.org/W4387332921","https://openalex.org/W4389072931","https://openalex.org/W4391156274","https://openalex.org/W6948426441"],"related_works":["https://openalex.org/W4301002638","https://openalex.org/W2163563073","https://openalex.org/W3186815950","https://openalex.org/W2371010743","https://openalex.org/W2606552659","https://openalex.org/W1987613674","https://openalex.org/W2181519036","https://openalex.org/W4253632195","https://openalex.org/W3088133960","https://openalex.org/W2202413591"],"abstract_inverted_index":{"Deep":[0],"clustering":[1,91],"(DC),":[2],"a":[3,66,89,134,206],"fusion":[4],"of":[5,28,101,171,181,191,197,209],"deep":[6,90],"representation":[7],"learning":[8,30],"and":[9,22,31,62,113,128,177,232,245],"clustering,":[10],"has":[11],"recently":[12],"demonstrated":[13],"positive":[14],"results":[15],"in":[16,34,141,219],"data":[17,32,53,56,67,79,83,95,102,140,173,203],"science,":[18],"particularly":[19,166],"text":[20],"processing":[21],"computer":[23],"vision.":[24],"However,":[25],"joint":[26],"optimization":[27],"feature":[29],"distribution":[33,156],"the":[35,78,99,131,158,169,195],"multi-dimensional":[36],"space":[37],"is":[38,165],"domain-specific,":[39],"so":[40],"existing":[41,198,227,242],"DC":[42,69,199,215],"methods":[43,235],"struggle":[44],"to":[45,47,74,81,150],"generalize":[46],"other":[48],"application":[49],"domains":[50],"(such":[51],"as":[52,157],"integration).":[54],"In":[55],"management":[57,103],"tasks,":[58],"where":[59,168],"high-density":[60],"embeddings":[61,170,204],"overlapping":[63,119],"clusters":[64,210],"dominate,":[65],"management-specific":[68],"algorithm":[70,92],"should":[71],"be":[72],"able":[73],"interact":[75],"better":[76],"with":[77,205,225],"properties":[80,100],"support":[82],"integration":[84,184],"tasks.":[85],"This":[86],"paper":[87],"presents":[88],"for":[93,138],"tabular":[94,139],"(TableDC)":[96],"that":[97,105],"reflects":[98],"applications":[104],"cluster":[106],"tables":[107],"(schema":[108],"inference),":[109],"rows":[110],"(entity":[111],"resolution)":[112],"columns":[114],"(domain":[115],"discovery).":[116],"To":[117],"address":[118],"clusters,":[120,192],"TableDC":[121,145,201,224,239],"integrates":[122],"Mahalanobis":[123],"distance,":[124],"which":[125,193,217],"considers":[126],"variance":[127],"correlation":[129],"within":[130],"data,":[132],"offering":[133],"similarity":[135,159,163],"method":[136],"suitable":[137],"high-dimensional":[142],"latent":[143],"spaces.":[144],"also":[146,187],"shows":[147],"higher":[148],"tolerance":[149],"outliers":[151],"through":[152],"its":[153],"heavy-tailed":[154],"Cauchy":[155],"kernel.":[160],"The":[161],"proposed":[162],"measure":[164],"beneficial":[167],"raw":[172],"are":[174],"densely":[175],"packed":[176],"exhibit":[178],"high":[179],"degrees":[180],"overlap.":[182],"Data":[183],"tasks":[185],"may":[186],"involve":[188],"large":[189,207],"numbers":[190],"challenges":[194],"scalability":[196],"methods.":[200,247],"learns":[202],"number":[208],"more":[211],"efficiently":[212],"than":[213],"baseline":[214],"methods,":[216],"scale":[218],"quadratic":[220],"time.":[221],"We":[222],"evaluated":[223],"several":[226],"DC,":[228,243],"Standard":[229],"Clustering":[230],"(SC),":[231],"state-of-the-art":[233],"bespoke":[234,246],"over":[236],"benchmark":[237],"datasets.":[238],"consistently":[240],"outperforms":[241],"SC":[244]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}