{"id":"https://openalex.org/W4220719590","doi":"https://doi.org/10.3390/fi14040110","title":"Decorrelation-Based Deep Learning for Bias Mitigation","display_name":"Decorrelation-Based Deep Learning for Bias Mitigation","publication_year":2022,"publication_date":"2022-03-29","ids":{"openalex":"https://openalex.org/W4220719590","doi":"https://doi.org/10.3390/fi14040110"},"language":"en","primary_location":{"id":"doi:10.3390/fi14040110","is_oa":true,"landing_page_url":"https://doi.org/10.3390/fi14040110","pdf_url":"https://www.mdpi.com/1999-5903/14/4/110/pdf?version=1648545604","source":{"id":"https://openalex.org/S34838331","display_name":"Future Internet","issn_l":"1999-5903","issn":["1999-5903"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Future Internet","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1999-5903/14/4/110/pdf?version=1648545604","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001728598","display_name":"Pranita Patil","orcid":"https://orcid.org/0000-0002-3679-3685"},"institutions":[{"id":"https://openalex.org/I153151563","display_name":"Harrisburg University of Science and Technology","ror":"https://ror.org/02g0s4z48","country_code":"US","type":"education","lineage":["https://openalex.org/I153151563"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Pranita Patil","raw_affiliation_strings":["Department of Analytics, Harrisburg University of Science and Technology, Harrisburg, PA 17101, USA"],"raw_orcid":"https://orcid.org/0000-0002-3679-3685","affiliations":[{"raw_affiliation_string":"Department of Analytics, Harrisburg University of Science and Technology, Harrisburg, PA 17101, USA","institution_ids":["https://openalex.org/I153151563"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001059956","display_name":"Kevin M. Purcell","orcid":"https://orcid.org/0000-0001-6046-2774"},"institutions":[{"id":"https://openalex.org/I153151563","display_name":"Harrisburg University of Science and Technology","ror":"https://ror.org/02g0s4z48","country_code":"US","type":"education","lineage":["https://openalex.org/I153151563"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin Purcell","raw_affiliation_strings":["Department of Analytics, Harrisburg University of Science and Technology, Harrisburg, PA 17101, USA"],"raw_orcid":"https://orcid.org/0000-0001-6046-2774","affiliations":[{"raw_affiliation_string":"Department of Analytics, Harrisburg University of Science and Technology, Harrisburg, PA 17101, USA","institution_ids":["https://openalex.org/I153151563"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5001728598"],"corresponding_institution_ids":["https://openalex.org/I153151563"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1466},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1466},"fwci":1.2809,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.80848873,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"14","issue":"4","first_page":"110","last_page":"110"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.9879000186920166,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.9879000186920166,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9854999780654907,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9769999980926514,"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/decorrelation","display_name":"Decorrelation","score":0.8744798898696899},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8289696574211121},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.7263635993003845},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6742111444473267},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.6334472298622131},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5433486104011536},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5064643621444702},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4853500425815582},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4819793105125427},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.41130900382995605},{"id":"https://openalex.org/keywords/mean-squared-error","display_name":"Mean squared error","score":0.41047677397727966},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3597177267074585},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.30317607522010803},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1555946171283722},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11805838346481323}],"concepts":[{"id":"https://openalex.org/C177860922","wikidata":"https://www.wikidata.org/wiki/Q788608","display_name":"Decorrelation","level":2,"score":0.8744798898696899},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8289696574211121},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.7263635993003845},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6742111444473267},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.6334472298622131},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5433486104011536},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5064643621444702},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4853500425815582},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4819793105125427},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.41130900382995605},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.41047677397727966},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3597177267074585},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.30317607522010803},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1555946171283722},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11805838346481323},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/fi14040110","is_oa":true,"landing_page_url":"https://doi.org/10.3390/fi14040110","pdf_url":"https://www.mdpi.com/1999-5903/14/4/110/pdf?version=1648545604","source":{"id":"https://openalex.org/S34838331","display_name":"Future Internet","issn_l":"1999-5903","issn":["1999-5903"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Future Internet","raw_type":"journal-article"},{"id":"pmh:oai:RePEc:gam:jftint:v:14:y:2022:i:4:p:110-:d:782137","is_oa":false,"landing_page_url":"https://www.mdpi.com/1999-5903/14/4/110/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},{"id":"pmh:oai:doaj.org/article:ae8cb9ed66484ea2aed115b24bea4d2b","is_oa":false,"landing_page_url":"https://doaj.org/article/ae8cb9ed66484ea2aed115b24bea4d2b","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Future Internet, Vol 14, Iss 4, p 110 (2022)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/fi14040110","is_oa":true,"landing_page_url":"https://doi.org/10.3390/fi14040110","pdf_url":"https://www.mdpi.com/1999-5903/14/4/110/pdf?version=1648545604","source":{"id":"https://openalex.org/S34838331","display_name":"Future Internet","issn_l":"1999-5903","issn":["1999-5903"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Future Internet","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5,"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4220719590.pdf"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1731081199","https://openalex.org/W2014352947","https://openalex.org/W2113952909","https://openalex.org/W2116984840","https://openalex.org/W2145979309","https://openalex.org/W2154579312","https://openalex.org/W2757251151","https://openalex.org/W2890680318","https://openalex.org/W2896803294","https://openalex.org/W2961158440","https://openalex.org/W2963116854","https://openalex.org/W2963350032","https://openalex.org/W2980810338","https://openalex.org/W2982358316","https://openalex.org/W3000374600","https://openalex.org/W3106063097","https://openalex.org/W3115055674","https://openalex.org/W3120895209","https://openalex.org/W3181414820","https://openalex.org/W4206709786","https://openalex.org/W4213263686","https://openalex.org/W4236706032","https://openalex.org/W6637618735","https://openalex.org/W6744110554","https://openalex.org/W6765646913","https://openalex.org/W7014198846"],"related_works":["https://openalex.org/W1604939135","https://openalex.org/W2127058578","https://openalex.org/W2098040275","https://openalex.org/W2735368845","https://openalex.org/W2089764958","https://openalex.org/W4206951940","https://openalex.org/W4293868382","https://openalex.org/W4382602594","https://openalex.org/W4387850423","https://openalex.org/W4313400923"],"abstract_inverted_index":{"Although":[0],"deep":[1,38,70,220],"learning":[2,39,71],"has":[3],"proven":[4],"to":[5,75,106,137,214],"be":[6,32],"tremendously":[7],"successful,":[8],"the":[9,13,19,27,58,69,129,144,156,164,169,216,225,234,238,258,265,274],"main":[10],"issue":[11],"is":[12,44,176,188],"dependency":[14,61],"of":[15,23,29,131,163,172,178,197,227,233,241,245,267,277,282,289],"its":[16],"performance":[17,276],"on":[18,42,190],"quality":[20,28],"and":[21,64,96,111,150,203,248],"quantity":[22],"training":[24],"datasets.":[25],"Since":[26],"data":[30,80],"can":[31],"affected":[33],"by":[34,56,78,102,140],"biases,":[35],"a":[36,123],"novel":[37],"method":[40,187,269],"based":[41],"decorrelation":[43,50,145],"presented":[45],"in":[46,122,126,219,280],"this":[47,139],"study.":[48],"The":[49,160,185],"specifically":[51],"learns":[52],"bias":[53,65,81,118,132,148,183,217,283],"invariant":[54],"features":[55,63],"reducing":[57],"non-linear":[59],"statistical":[60],"between":[62],"itself.":[66],"This":[67],"makes":[68],"models":[72,256],"less":[73],"prone":[74],"biased":[76],"decisions":[77],"addressing":[79],"issues.":[82],"We":[83],"introduce":[84],"Decorrelated":[85,91,97],"Deep":[86,107],"Neural":[87,93,99,108,113],"Networks":[88,94,100,109,114],"(DcDNN)":[89],"or":[90],"Convolutional":[92],"(DcCNN)":[95],"Artificial":[98,112],"(DcANN)":[101],"applying":[103],"decorrelation-based":[104],"optimization":[105],"(DNN)":[110],"(ANN),":[115],"respectively.":[116],"Previous":[117],"mitigation":[119,218],"methods":[120,272],"result":[121],"drastic":[124],"loss":[125,151],"accuracy":[127,154,180,249,262],"at":[128],"cost":[130],"reduction.":[133],"Our":[134],"study":[135],"aims":[136],"resolve":[138],"controlling":[141],"how":[142],"strongly":[143],"function":[146,152],"for":[147,153,168],"reduction":[149],"affect":[155],"network":[157],"objective":[158],"function.":[159],"detailed":[161],"analysis":[162,244],"hyperparameter":[165],"shows":[166,251,273],"that":[167,252],"optimal":[170],"value":[171],"hyperparameter,":[173],"our":[174,208,254,268,278],"model":[175,236,279],"capable":[177],"maintaining":[179],"while":[181],"being":[182],"invariant.":[184],"proposed":[186,235,255],"evaluated":[189],"several":[191],"benchmark":[192],"datasets":[193],"with":[194,211,270],"different":[195],"types":[196],"biases":[198,259],"such":[199],"as":[200,285,287],"age,":[201],"gender,":[202],"color.":[204],"Additionally,":[205],"we":[206],"test":[207],"approach":[209],"along":[210],"traditional":[212],"approaches":[213],"analyze":[215],"learning.":[221],"Using":[222],"simulated":[223],"datasets,":[224],"results":[226],"t-distributed":[228],"stochastic":[229],"neighbor":[230],"embedding":[231],"(t-SNE)":[232],"validated":[237],"effective":[239],"removal":[240],"bias.":[242],"An":[243],"fairness":[246],"metrics":[247],"comparisons":[250],"using":[253],"reduces":[257],"without":[260],"compromising":[261],"significantly.":[263],"Furthermore,":[264],"comparison":[266],"existing":[271],"superior":[275],"terms":[281],"mitigation,":[284],"well":[286],"simplicity":[288],"training.":[290]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}