{"id":"https://openalex.org/W4409882769","doi":"https://doi.org/10.1109/tkde.2025.3564313","title":"Turn Waste Into Wealth: On Efficient Clustering and Cleaning Over Dirty Data","display_name":"Turn Waste Into Wealth: On Efficient Clustering and Cleaning Over Dirty Data","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4409882769","doi":"https://doi.org/10.1109/tkde.2025.3564313"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2025.3564313","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2025.3564313","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058179465","display_name":"Kenny Ye Liang","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kenny Ye Liang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026003458","display_name":"Yunxiang Su","orcid":"https://orcid.org/0009-0004-7584-6913"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunxiang Su","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084430029","display_name":"Shaoxu Song","orcid":"https://orcid.org/0000-0002-9503-2755"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaoxu Song","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100687714","display_name":"Chunping Li","orcid":"https://orcid.org/0000-0001-6184-1485"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunping Li","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5058179465"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11729099,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.8640999794006348,"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"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.8640999794006348,"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":0.7450188398361206},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6975232362747192},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33912280201911926},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.32067400217056274},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21705362200737}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7450188398361206},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6975232362747192},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33912280201911926},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.32067400217056274},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21705362200737}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tkde.2025.3564313","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2025.3564313","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6100000143051147,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1612155886","https://openalex.org/W1987111416","https://openalex.org/W2002928429","https://openalex.org/W2004683304","https://openalex.org/W2045054164","https://openalex.org/W2092799168","https://openalex.org/W2137130182","https://openalex.org/W2162833336","https://openalex.org/W2163600218","https://openalex.org/W2167333415","https://openalex.org/W2236116266","https://openalex.org/W2380172038","https://openalex.org/W2570579522","https://openalex.org/W2613529642","https://openalex.org/W2734096706","https://openalex.org/W2799132955","https://openalex.org/W2951598055","https://openalex.org/W2953048192","https://openalex.org/W2971187863","https://openalex.org/W3110435694","https://openalex.org/W3174526319","https://openalex.org/W3174918961","https://openalex.org/W4213009331","https://openalex.org/W4281778754","https://openalex.org/W4312615758","https://openalex.org/W4381326806","https://openalex.org/W4385568201","https://openalex.org/W4392611810","https://openalex.org/W4404644535","https://openalex.org/W6631782964","https://openalex.org/W6681534161","https://openalex.org/W6687188548","https://openalex.org/W6756034256"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Dirty":[0],"data":[1,23,48,60,80,161],"commonly":[2],"exist.":[3],"Simply":[4],"discarding":[5],"a":[6,39,67],"large":[7,76],"number":[8],"of":[9,42,70,78,155],"inaccurate":[10,71],"points":[11,72],"(as":[12],"noises)":[13],"could":[14],"greatly":[15],"affect":[16],"clustering":[17,43,131,145],"results.":[18],"We":[19,84],"argue":[20],"that":[21,74,86,140],"dirty":[22,47,79,160],"can":[24,81,94,149],"be":[25,95,150],"repaired":[26],"and":[27,44,93,130,146,157],"utilized":[28],"as":[29,97],"strong":[30],"supports":[31],"in":[32,59,162],"clustering.":[33,83,163],"To":[34],"this":[35],"end,":[36],"we":[37],"study":[38],"novel":[40],"problem":[41,88],"repairing":[45,129,156],"over":[46],"at":[49],"the":[50,55,62,75,87,144,159],"same":[51],"time.":[52],"Referring":[53],"to":[54,65],"minimum":[56,68],"change":[57],"principle":[58],"repairing,":[61],"objective":[63],"is":[64,89,114],"find":[66],"modification":[69],"such":[73],"amount":[77],"enhance":[82],"show":[85],"<sc":[90,111,124],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[91,103,112,125,142],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">NP</small>-hard":[92],"formulated":[96],"an":[98],"integer":[99],"linear":[100],"programming":[101],"(<sc":[102],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">ILP</small>)":[104],"problem.":[105],"A":[106],"constant":[107],"factor":[108],"approximation":[109],"algorithm":[110],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">GDORC</small>":[113,126],"devised":[115],"based":[116],"on":[117],"grid,":[118],"with":[119,133],"high":[120],"efficiency.":[121],"In":[122],"experiments,":[123],"has":[127],"great":[128],"results":[132,138],"low":[134],"time":[135],"consumption.":[136],"Empirical":[137],"demonstrate":[139],"<italic":[141],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">both":[143],"cleaning":[147],"accuracies</i>":[148],"improved":[151],"by":[152],"our":[153],"approach":[154],"utilizing":[158]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}