{"id":"https://openalex.org/W4390264179","doi":"https://doi.org/10.1007/s10994-023-06451-5","title":"Sanitized clustering against confounding bias","display_name":"Sanitized clustering against confounding bias","publication_year":2023,"publication_date":"2023-12-27","ids":{"openalex":"https://openalex.org/W4390264179","doi":"https://doi.org/10.1007/s10994-023-06451-5"},"language":"en","primary_location":{"id":"doi:10.1007/s10994-023-06451-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-023-06451-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-023-06451-5.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10994-023-06451-5.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004970804","display_name":"Yinghua Yao","orcid":"https://orcid.org/0000-0003-3204-0739"},"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"]},{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["AU","CN","SG"],"is_corresponding":true,"raw_author_name":"Yinghua Yao","raw_affiliation_strings":["Australian Artificial Intelligence Institute, University of Technology Sydney (UTS), Sydney,  2007, Australia","CFAR , Agency for Science, Technology, and Research (A*STAR), Singapore, 138632, Singapore","Computer Science and Enigineering, Southern University of Science and Technology (SUSTech), Shenzhen, 518055, China","IHPC, Agency for Science, Technology, and Research (A*STAR), Singapore, 138632, Singapore"],"raw_orcid":"https://orcid.org/0000-0003-3204-0739","affiliations":[{"raw_affiliation_string":"Australian Artificial Intelligence Institute, University of Technology Sydney (UTS), Sydney,  2007, Australia","institution_ids":["https://openalex.org/I114017466"]},{"raw_affiliation_string":"CFAR , Agency for Science, Technology, and Research (A*STAR), Singapore, 138632, Singapore","institution_ids":["https://openalex.org/I115228651"]},{"raw_affiliation_string":"Computer Science and Enigineering, Southern University of Science and Technology (SUSTech), Shenzhen, 518055, China","institution_ids":["https://openalex.org/I3045169105"]},{"raw_affiliation_string":"IHPC, Agency for Science, Technology, and Research (A*STAR), Singapore, 138632, Singapore","institution_ids":["https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020554727","display_name":"Yuangang Pan","orcid":"https://orcid.org/0000-0002-7950-4900"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yuangang Pan","raw_affiliation_strings":["CFAR , Agency for Science, Technology, and Research (A*STAR), Singapore, 138632, Singapore","IHPC, Agency for Science, Technology, and Research (A*STAR), Singapore, 138632, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CFAR , Agency for Science, Technology, and Research (A*STAR), Singapore, 138632, Singapore","institution_ids":["https://openalex.org/I115228651"]},{"raw_affiliation_string":"IHPC, Agency for Science, Technology, and Research (A*STAR), Singapore, 138632, Singapore","institution_ids":["https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100336792","display_name":"Jing Li","orcid":"https://orcid.org/0000-0001-7584-1240"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jing Li","raw_affiliation_strings":["CFAR , Agency for Science, Technology, and Research (A*STAR), Singapore, 138632, Singapore","IHPC, Agency for Science, Technology, and Research (A*STAR), Singapore, 138632, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CFAR , Agency for Science, Technology, and Research (A*STAR), Singapore, 138632, Singapore","institution_ids":["https://openalex.org/I115228651"]},{"raw_affiliation_string":"IHPC, Agency for Science, Technology, and Research (A*STAR), Singapore, 138632, Singapore","institution_ids":["https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021751767","display_name":"Ivor W. Tsang","orcid":"https://orcid.org/0000-0001-8095-4637"},"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"]},{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["AU","SG"],"is_corresponding":false,"raw_author_name":"Ivor W. Tsang","raw_affiliation_strings":["Australian Artificial Intelligence Institute, University of Technology Sydney (UTS), Sydney,  2007, Australia","CFAR , Agency for Science, Technology, and Research (A*STAR), Singapore, 138632, Singapore","IHPC, Agency for Science, Technology, and Research (A*STAR), Singapore, 138632, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Australian Artificial Intelligence Institute, University of Technology Sydney (UTS), Sydney,  2007, Australia","institution_ids":["https://openalex.org/I114017466"]},{"raw_affiliation_string":"CFAR , Agency for Science, Technology, and Research (A*STAR), Singapore, 138632, Singapore","institution_ids":["https://openalex.org/I115228651"]},{"raw_affiliation_string":"IHPC, Agency for Science, Technology, and Research (A*STAR), Singapore, 138632, Singapore","institution_ids":["https://openalex.org/I115228651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100635494","display_name":"Xin Yao","orcid":"https://orcid.org/0000-0001-8837-4442"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Yao","raw_affiliation_strings":["Computer Science and Enigineering, Southern University of Science and Technology (SUSTech), Shenzhen, 518055, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Enigineering, Southern University of Science and Technology (SUSTech), Shenzhen, 518055, China","institution_ids":["https://openalex.org/I3045169105"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5004970804"],"corresponding_institution_ids":["https://openalex.org/I114017466","https://openalex.org/I115228651","https://openalex.org/I3045169105"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":0.3408,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.67885863,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"113","issue":"6","first_page":"3711","last_page":"3730"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9994000196456909,"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":0.9994000196456909,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9983000159263611,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9980999827384949,"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/confounding","display_name":"Confounding","score":0.8269121646881104},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.8042329549789429},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.5033201575279236},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4708143174648285},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.410054087638855},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39433830976486206},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.38567492365837097},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3762555718421936},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33244162797927856}],"concepts":[{"id":"https://openalex.org/C77350462","wikidata":"https://www.wikidata.org/wiki/Q1125472","display_name":"Confounding","level":2,"score":0.8269121646881104},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8042329549789429},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.5033201575279236},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4708143174648285},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.410054087638855},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39433830976486206},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.38567492365837097},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3762555718421936},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33244162797927856}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10994-023-06451-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-023-06451-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-023-06451-5.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10994-023-06451-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-023-06451-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-023-06451-5.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390264179.pdf"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W134960717","https://openalex.org/W1663973292","https://openalex.org/W1722318740","https://openalex.org/W1763538293","https://openalex.org/W1959178355","https://openalex.org/W1992419399","https://openalex.org/W2002394060","https://openalex.org/W2022686119","https://openalex.org/W2097664646","https://openalex.org/W2100659887","https://openalex.org/W2102751249","https://openalex.org/W2107665951","https://openalex.org/W2112796928","https://openalex.org/W2116650193","https://openalex.org/W2139345901","https://openalex.org/W2145094598","https://openalex.org/W2166549811","https://openalex.org/W2535873859","https://openalex.org/W2730106296","https://openalex.org/W2741943936","https://openalex.org/W2752796333","https://openalex.org/W2899477140","https://openalex.org/W2905631704","https://openalex.org/W2970795117","https://openalex.org/W3034363127","https://openalex.org/W3034747430","https://openalex.org/W3035524453","https://openalex.org/W3129931824","https://openalex.org/W3137513727","https://openalex.org/W3175397654","https://openalex.org/W6607151510","https://openalex.org/W6654170900","https://openalex.org/W6685380521","https://openalex.org/W6729906282","https://openalex.org/W6743933341","https://openalex.org/W6773831323","https://openalex.org/W6790925374"],"related_works":["https://openalex.org/W2994176440","https://openalex.org/W2481749367","https://openalex.org/W2510575233","https://openalex.org/W2495367848","https://openalex.org/W830718730","https://openalex.org/W2793477322","https://openalex.org/W4236720793","https://openalex.org/W1992228662","https://openalex.org/W2503931704","https://openalex.org/W4246786946"],"abstract_inverted_index":{"Abstract":[0],"Real-world":[1],"datasets":[2,188],"inevitably":[3],"contain":[4],"biases":[5,34],"that":[6,25,190],"arise":[7],"from":[8],"different":[9],"sources":[10],"or":[11],"conditions":[12],"during":[13],"data":[14,37,74,97,136],"collection.":[15],"Consequently,":[16],"such":[17],"inconsistency":[18],"itself":[19],"acts":[20],"as":[21,95],"a":[22,114,138,172,194],"confounding":[23,48,59,77,109,122,127,161,203],"factor":[24,49,56,60,78,128,162],"disturbs":[26],"the":[27,33,39,43,47,53,58,65,70,73,76,96,108,126,130,147,151,156,160,164,180,202],"cluster":[28,178],"analysis.":[29],"Existing":[30],"methods":[31],"eliminate":[32,146],"by":[35,46,154,168,200],"projecting":[36],"onto":[38],"orthogonal":[40],"complement":[41],"of":[42,134],"subspace":[44],"expanded":[45],"before":[50],"clustering.":[51],"Therein,":[52],"interested":[54],"clustering":[55,116,173,198],"and":[57,75,104,163],"are":[61,90],"coarsely":[62],"considered":[63],"in":[64,93,98,129,150,197],"raw":[66],"feature":[67],"space,":[68],"where":[69],"correlation":[71],"between":[72,159],"is":[79,101,175],"ideally":[80],"assumed":[81],"to":[82,177],"be":[83,143],"linear":[84],"for":[85],"convenient":[86],"solutions.":[87],"These":[88],"approaches":[89],"thus":[91],"limited":[92],"scope":[94],"real":[99],"applications":[100],"usually":[102],"complex":[103,135,187],"non-linearly":[105],"correlated":[106],"with":[107],"factor.":[110],"This":[111],"paper":[112],"presents":[113],"new":[115],"framework":[117],"named":[118],"Sanitized":[119],"Clustering":[120],"Against":[121],"Bias,":[123],"which":[124],"removes":[125],"semantic":[131],"latent":[132,152,165,182],"space":[133,153],"through":[137],"non-linear":[139],"dependence":[140],"measure.":[141],"To":[142],"specific,":[144],"we":[145],"bias":[148],"information":[149,158],"minimizing":[155],"mutual":[157],"representation":[166],"delivered":[167],"variational":[169],"auto-encoder.":[170],"Meanwhile,":[171],"module":[174],"introduced":[176],"over":[179],"purified":[181],"representations.":[183],"Extensive":[184],"experiments":[185],"on":[186],"demonstrate":[189],"our":[191],"SCAB":[192],"achieves":[193],"significant":[195],"gain":[196],"performance":[199],"removing":[201],"bias.":[204]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-21T23:12:01.093139","created_date":"2025-10-10T00:00:00"}