{"id":"https://openalex.org/W4409584081","doi":"https://doi.org/10.1145/3730577","title":"Less Is More: Feature Engineering for Fairness and Performance of Machine Learning Software","display_name":"Less Is More: Feature Engineering for Fairness and Performance of Machine Learning Software","publication_year":2025,"publication_date":"2025-04-18","ids":{"openalex":"https://openalex.org/W4409584081","doi":"https://doi.org/10.1145/3730577"},"language":"en","primary_location":{"id":"doi:10.1145/3730577","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3730577","pdf_url":null,"source":{"id":"https://openalex.org/S142627899","display_name":"ACM Transactions on Software Engineering and Methodology","issn_l":"1049-331X","issn":["1049-331X","1557-7392"],"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":"ACM Transactions on Software Engineering and Methodology","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/A5019161243","display_name":"Linghan Meng","orcid":null},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Linghan Meng","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","State Key Laboratory for Novel Software Technology, Nanjing University, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100360608","display_name":"Yanhui Li","orcid":"https://orcid.org/0000-0003-2282-7175"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanhui Li","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","State Key Laboratory for Novel Software Technology, Nanjing University, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100443798","display_name":"Lin Chen","orcid":"https://orcid.org/0000-0003-2352-2226"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Chen","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","State Key Laboratory for Novel Software Technology, Nanjing University, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109432614","display_name":"Mingliang Ma","orcid":"https://orcid.org/0000-0002-4800-6255"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingliang Ma","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","State Key Laboratory for Novel Software Technology, Nanjing University, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031391841","display_name":"Yuming Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuming Zhou","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","State Key Laboratory for Novel Software Technology, Nanjing University, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100331400","display_name":"Baowen Xu","orcid":"https://orcid.org/0000-0001-7743-1296"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baowen Xu","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","State Key Laboratory for Novel Software Technology, Nanjing University, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5019161243"],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":5.0819,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.94545986,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"35","issue":"2","first_page":"1","last_page":"36"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine 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"}},"topics":[{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine 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/T12535","display_name":"Machine Learning and Data Classification","score":0.9948999881744385,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.9945999979972839,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8379268646240234},{"id":"https://openalex.org/keywords/feature-engineering","display_name":"Feature engineering","score":0.5403885841369629},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.5315746068954468},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5161719918251038},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.42818811535835266},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3867279589176178},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1250706911087036},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.12376615405082703}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8379268646240234},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.5403885841369629},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.5315746068954468},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5161719918251038},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.42818811535835266},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3867279589176178},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1250706911087036},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.12376615405082703},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3730577","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3730577","pdf_url":null,"source":{"id":"https://openalex.org/S142627899","display_name":"ACM Transactions on Software Engineering and Methodology","issn_l":"1049-331X","issn":["1049-331X","1557-7392"],"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":"ACM Transactions on Software Engineering and Methodology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W207758080","https://openalex.org/W1596515083","https://openalex.org/W1685464609","https://openalex.org/W1995675879","https://openalex.org/W2014352947","https://openalex.org/W2048087720","https://openalex.org/W2097246321","https://openalex.org/W2109293916","https://openalex.org/W2143426320","https://openalex.org/W2250086655","https://openalex.org/W2293505944","https://openalex.org/W2561675875","https://openalex.org/W2666681845","https://openalex.org/W2730550703","https://openalex.org/W2776928536","https://openalex.org/W2809701591","https://openalex.org/W2887809151","https://openalex.org/W2898435572","https://openalex.org/W2901941771","https://openalex.org/W2912324183","https://openalex.org/W2914761779","https://openalex.org/W2922234936","https://openalex.org/W2922408684","https://openalex.org/W2964211521","https://openalex.org/W2967682612","https://openalex.org/W2971364334","https://openalex.org/W2995639860","https://openalex.org/W2995858837","https://openalex.org/W3002398329","https://openalex.org/W3007157104","https://openalex.org/W3014011525","https://openalex.org/W3022364011","https://openalex.org/W3032152562","https://openalex.org/W3038416089","https://openalex.org/W3046701849","https://openalex.org/W3102138742","https://openalex.org/W3118657661","https://openalex.org/W3127971289","https://openalex.org/W3134513786","https://openalex.org/W3162632914","https://openalex.org/W3166873126","https://openalex.org/W3176309799","https://openalex.org/W3179976352","https://openalex.org/W3192727323","https://openalex.org/W3194588521","https://openalex.org/W4205409254","https://openalex.org/W4205596332","https://openalex.org/W4205626510","https://openalex.org/W4206787394","https://openalex.org/W4220659214","https://openalex.org/W4220958110","https://openalex.org/W4226228033","https://openalex.org/W4226256920","https://openalex.org/W4234971943","https://openalex.org/W4236606190","https://openalex.org/W4239249613","https://openalex.org/W4241857777","https://openalex.org/W4284697101","https://openalex.org/W4284701600","https://openalex.org/W4297847306","https://openalex.org/W4308641598","https://openalex.org/W4308643994","https://openalex.org/W4308731725","https://openalex.org/W6638249342","https://openalex.org/W6768681878","https://openalex.org/W6809846253"],"related_works":["https://openalex.org/W4398232961","https://openalex.org/W4387478977","https://openalex.org/W3147584709","https://openalex.org/W2977677679","https://openalex.org/W2750075801","https://openalex.org/W3164948662","https://openalex.org/W4400413234","https://openalex.org/W3153597579","https://openalex.org/W4394398790","https://openalex.org/W4399455186"],"abstract_inverted_index":{"Machine":[0],"Learning":[1],"(ML)":[2],"software":[3,300,314],"employs":[4,253],"statistical":[5],"algorithms":[6],"to":[7,21,37,85,119,153,188,195,206,234,239,257,266,282,305],"perform":[8],"high-stake":[9],"tasks":[10],"in":[11,103,122],"our":[12,284],"daily":[13],"lives,":[14],"whose":[15],"results":[16,290],"are":[17,182],"usually":[18],"discriminatory":[19],"due":[20],"protected":[22,113,161],"features":[23,162,181,197,310],"(e.g.,":[24],"gender),":[25],"i.e.,":[26,92,179],"one":[27,90],"part":[28,44],"(called":[29,45],"privileged,":[30],"e.g.,":[31,47],"male)":[32],"may":[33],"be":[34,120],"more":[35,180,196,199],"likely":[36],"obtain":[38],"beneficial":[39],"decisions":[40],"than":[41],"the":[42,51,60,78,82,100,104,110,132,138,160,177,214,241,268,342],"other":[43],"unprivileged,":[46],"female).":[48],"In":[49,144],"alleviating":[50],"unfairness,":[52],"developers":[53],"have":[54,116,291],"obtained":[55],"widely":[56],"held":[57],"beliefs":[58],"about":[59,307],"tradeoff":[61,139,170],"between":[62,140,171],"performance":[63,96,141,172,190,247,259,319],"and":[64,97,126,142,163,173,191,201,227,248,260,262,279,320,322],"fairness":[65,174,261],"for":[66,208,298],"ML":[67,299,313],"software.":[68],"Surprisingly,":[69],"recent":[70],"research":[71],"on":[72,276],"feature":[73,79,223,243,255,301,344],"engineering":[74],"suggests":[75],"that":[76,165,293],"enlarging":[77,176],"set":[80,244],"is":[81,167,216,296,325],"perfect":[83],"way":[84],"kill":[86],"two":[87],"birds":[88],"with":[89,175,245,286,315,327,333],"stone,":[91],"achieving":[93],"both":[94,123],"higher":[95,189],"fairness.":[98,143,193,249],"However,":[99],"experiments":[101,275],"used":[102],"prior":[105,156],"study":[106,133,152,157],"did":[107,134],"not":[108,135,183],"remove":[109],"effect":[111],"of":[112,270,309],"features,":[114,178],"which":[115,185],"been":[117],"suggested":[118],"excluded":[121],"industrial":[124],"applications":[125],"academic":[127],"studies.":[128],"As":[129],"a":[130,169,221],"result,":[131],"fully":[136],"explore":[137],"this":[145,155],"article,":[146],"we":[147,204,219],"first":[148],"conduct":[149,274],"an":[150,209,236],"empirical":[151],"replicate":[154],"after":[158],"excluding":[159],"observe":[164],"there":[166],"still":[168,339],"perfect,":[184],"would":[186,311,338],"lead":[187],"lower":[192],"Due":[194],"causing":[198],"collection":[200],"pre-processing":[202],"budgets,":[203],"aim":[205],"search":[207],"effective":[210],"alternative.":[211],"Inspired":[212],"by":[213],"\u201cless":[215],"more\u201d":[217],"principle,":[218],"propose":[220],"novel":[222],"ranking":[224],"method,":[225,251],"Hybrid-importance":[226],"Early-validation":[228],"based":[229],"Feature":[230],"Ranking":[231],"(HEFR)":[232],",":[233],"find":[235],"efficient":[237,297],"subset":[238],"replace":[240],"full":[242],"comparable":[246,318],"Our":[250],"HEFR,":[252],"hybrid":[254,271],"importances":[256],"combine":[258],"conducts":[263],"early":[264],"validation":[265],"check":[267],"effectiveness":[269],"importances.":[272],"We":[273],"seven":[277],"datasets":[278],"three":[280],"classifiers":[281],"evaluate":[283],"method":[285],"five":[287],"baselines.":[288],"The":[289],"shown":[292],"(a)":[294],"HEFR":[295,304,324,332],"engineering:":[302],"applying":[303,331],"choose":[306,341],"10%":[308,335],"construct":[312],"better":[316],"or":[317],"fairness,":[321],"(b)":[323],"actionable":[326],"small":[328],"dataset":[329],"sizes:":[330],"only":[334],"data":[336],"size":[337],"help":[340],"proper":[343],"subset.":[345]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-03-26T15:22:09.906841","created_date":"2025-10-10T00:00:00"}