{"id":"https://openalex.org/W4404126154","doi":"https://doi.org/10.1145/3695831","title":"Improved Approximation Algorithms for Relational Clustering","display_name":"Improved Approximation Algorithms for Relational Clustering","publication_year":2024,"publication_date":"2024-11-04","ids":{"openalex":"https://openalex.org/W4404126154","doi":"https://doi.org/10.1145/3695831"},"language":"en","primary_location":{"id":"doi:10.1145/3695831","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3695831","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3695831","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":null,"license_id":null,"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":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3695831","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114419945","display_name":"Aryan Esmailpour","orcid":null},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aryan Esmailpour","raw_affiliation_strings":["Department of Computer Science, University of Illinois Chicago, Chicago, USA"],"raw_orcid":"https://orcid.org/0009-0000-3798-9578","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Illinois Chicago, Chicago, USA","institution_ids":["https://openalex.org/I39422238"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015883931","display_name":"Stavros Sintos","orcid":"https://orcid.org/0000-0002-2114-8886"},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stavros Sintos","raw_affiliation_strings":["Department of Computer Science, University of Illinois Chicago, Chicago, USA"],"raw_orcid":"https://orcid.org/0000-0002-2114-8886","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Illinois Chicago, Chicago, USA","institution_ids":["https://openalex.org/I39422238"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I39422238"],"apc_list":null,"apc_paid":null,"fwci":0.4242,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.58094556,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"2","issue":"5","first_page":"1","last_page":"27"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9993000030517578,"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"}},"topics":[{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9993000030517578,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.998199999332428,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9972000122070312,"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/cluster-analysis","display_name":"Cluster analysis","score":0.6625101566314697},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5451357960700989},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.46190956234931946},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28743723034858704}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6625101566314697},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5451357960700989},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.46190956234931946},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28743723034858704}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3695831","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3695831","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3695831","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":null,"license_id":null,"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:10.1145/3695831","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3695831","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3695831","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":null,"license_id":null,"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/G4595059316","display_name":"III: Small: Fairness-aware Data Structures for Approximate Query Processing","funder_award_id":"2348919","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6833551468","display_name":null,"funder_award_id":"IIS-2348919","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404126154.pdf","grobid_xml":"https://content.openalex.org/works/W4404126154.grobid-xml"},"referenced_works_count":51,"referenced_works":["https://openalex.org/W166438205","https://openalex.org/W1522217894","https://openalex.org/W1530581016","https://openalex.org/W1977983731","https://openalex.org/W2010410498","https://openalex.org/W2023770210","https://openalex.org/W2032775418","https://openalex.org/W2034574601","https://openalex.org/W2034616054","https://openalex.org/W2045964207","https://openalex.org/W2087916849","https://openalex.org/W2108399535","https://openalex.org/W2123297508","https://openalex.org/W2150593711","https://openalex.org/W2161956202","https://openalex.org/W2165420145","https://openalex.org/W2169998163","https://openalex.org/W2199495299","https://openalex.org/W2247380138","https://openalex.org/W2284514301","https://openalex.org/W2300196885","https://openalex.org/W2604519798","https://openalex.org/W2626428686","https://openalex.org/W2807006342","https://openalex.org/W2885849839","https://openalex.org/W2906408488","https://openalex.org/W2950050514","https://openalex.org/W2962991166","https://openalex.org/W2982739078","https://openalex.org/W2997488476","https://openalex.org/W3030153809","https://openalex.org/W3144298286","https://openalex.org/W3145543370","https://openalex.org/W3177418610","https://openalex.org/W4206206918","https://openalex.org/W4210631930","https://openalex.org/W4251646134","https://openalex.org/W4252017042","https://openalex.org/W4285136459","https://openalex.org/W4304701435","https://openalex.org/W4313476522","https://openalex.org/W4317940023","https://openalex.org/W4378713432","https://openalex.org/W4404130423","https://openalex.org/W6678451095","https://openalex.org/W6721489668","https://openalex.org/W6758554399","https://openalex.org/W6768567772","https://openalex.org/W6781077187","https://openalex.org/W6817629744","https://openalex.org/W6845989552"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2051487156","https://openalex.org/W2073681303","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109"],"abstract_inverted_index":{"Clustering":[0],"plays":[1],"a":[2,145,150,192,221],"crucial":[3],"role":[4],"in":[5,45,177,225],"computer":[6],"science,":[7],"facilitating":[8],"data":[9,49,85],"analysis":[10],"and":[11,27,41,80,121,149,160,209,215],"problem-solving":[12],"across":[13,52],"numerous":[14],"fields.":[15],"By":[16],"partitioning":[17],"large":[18,136],"datasets":[19],"into":[20],"meaningful":[21],"groups,":[22],"clustering":[23,56,82,130,162,223],"reveals":[24],"hidden":[25],"structures":[26],"relationships":[28],"within":[29],"the":[30,63,87,91,96,102,109,118,122,126,164,197,201,212,216,226],"data,":[31],"aiding":[32],"tasks":[33],"such":[34],"as":[35],"unsupervised":[36],"learning,":[37],"classification,":[38],"anomaly":[39],"detection,":[40],"recommendation":[42],"systems.":[43],"Particularly":[44],"relational":[46,84,97,110,128],"databases,":[47],"where":[48,187],"is":[50,57,191,200],"distributed":[51],"multiple":[53],"tables,":[54],"efficient":[55,76,104],"essential":[58],"yet":[59],"challenging":[60],"due":[61],"to":[62],"computational":[64,228],"complexity":[65],"of":[66,125,154,166,205,220],"joining":[67],"tables.":[68],"This":[69],"paper":[70],"addresses":[71],"this":[72],"challenge":[73],"by":[74,196],"introducing":[75],"algorithms":[77,174],"for":[78,89,157],"k-median":[79,98,159],"k-means":[81,111,129,161],"on":[83,163,168],"without":[86],"need":[88],"pre-computing":[90],"join":[92,146],"query":[93,147],"results.":[94],"For":[95,108],"clustering,":[99,112],"we":[100,170],"propose":[101,171],"first":[103],"relative":[105],"approximation":[106,119,138,213],"algorithm.":[107],"our":[113],"algorithm":[114,224],"significantly":[115],"improves":[116],"both":[117,158],"factor":[120,214],"running":[123,142,217],"time":[124],"known":[127],"algorithms,":[131],"which":[132],"suffer":[133],"either":[134],"from":[135],"constant":[137,193],"factors,":[139],"or":[140],"expensive":[141],"time.":[143],"Given":[144],"q":[148,167],"database":[151],"instance":[152],"D":[153],"O(N)":[155],"tuples,":[156],"results":[165],"D,":[169],"randomized":[172],"(1+\u03b5)\u03b3-approximation":[173],"that":[175],"run":[176],"roughly":[178],"O(k":[179],"2":[180,184],"N":[181],"fhw":[182],")+T_\u03b3(k":[183],")":[185],"time,":[186,218],"\u03b5":[188],"\u2208":[189],"(0,1)":[190],"parameter":[194],"decided":[195],"user,":[198],"\\fhw":[199],"fractional":[202],"hyper-tree":[203],"width":[204],"Q,":[206],"while":[207],"\u03b3":[208],"T_\u03b3(x)":[210],"represent":[211],"respectively,":[219],"traditional":[222],"standard":[227],"setting":[229],"over":[230],"x":[231],"points.":[232]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}