{"id":"https://openalex.org/W7131435479","doi":"https://doi.org/10.48550/arxiv.2602.20001","title":"FairFS: Addressing Deep Feature Selection Biases for Recommender System","display_name":"FairFS: Addressing Deep Feature Selection Biases for Recommender System","publication_year":2026,"publication_date":"2026-02-23","ids":{"openalex":"https://openalex.org/W7131435479","doi":"https://doi.org/10.48550/arxiv.2602.20001"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2602.20001","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.20001","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2602.20001","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058613427","display_name":"Xianquan Wang","orcid":"https://orcid.org/0009-0003-9744-220X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wang, Xianquan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126785030","display_name":"Zhaocheng Du","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Du, Zhaocheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126834679","display_name":"Jieming Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Jieming","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126788199","display_name":"Qinglin Jia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jia, Qinglin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033937910","display_name":"Zhenhua Dong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dong, Zhenhua","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5126780319","display_name":"Kai Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Kai","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5058613427"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.6549000144004822,"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":0.6549000144004822,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.09470000118017197,"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"}},{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.05700000002980232,"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/feature-selection","display_name":"Feature selection","score":0.7980999946594238},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.6830999851226807},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.6622999906539917},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.629800021648407},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6037999987602234},{"id":"https://openalex.org/keywords/decision-boundary","display_name":"Decision boundary","score":0.4945000112056732},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.37790000438690186}],"concepts":[{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.7980999946594238},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7771000266075134},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.6830999851226807},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.6622999906539917},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6438999772071838},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.629800021648407},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6037999987602234},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5612000226974487},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5515999794006348},{"id":"https://openalex.org/C42023084","wikidata":"https://www.wikidata.org/wiki/Q5249231","display_name":"Decision boundary","level":3,"score":0.4945000112056732},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.37790000438690186},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.3709999918937683},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.36809998750686646},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.328000009059906},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32749998569488525},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.2919999957084656},{"id":"https://openalex.org/C40423286","wikidata":"https://www.wikidata.org/wiki/Q284172","display_name":"Selection bias","level":2,"score":0.2913999855518341},{"id":"https://openalex.org/C110083411","wikidata":"https://www.wikidata.org/wiki/Q1744628","display_name":"Statistical classification","level":2,"score":0.26499998569488525},{"id":"https://openalex.org/C139532973","wikidata":"https://www.wikidata.org/wiki/Q2679259","display_name":"Linear classifier","level":3,"score":0.26010000705718994}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2602.20001","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.20001","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2602.20001","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.20001","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.5600558519363403}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large-scale":[0],"online":[1,50,56],"marketplaces":[2],"and":[3,72,78,125,137,169,178,190],"recommender":[4,16],"systems":[5],"serve":[6],"as":[7,22,120],"critical":[8,34],"technological":[9],"support":[10],"for":[11,26,49],"e-commerce":[12],"development.":[13],"In":[14],"industrial":[15,82],"systems,":[17],"features":[18],"play":[19],"vital":[20],"roles":[21],"they":[23],"carry":[24],"information":[25],"downstream":[27],"models.":[28],"Accurate":[29],"feature":[30,42,47,64,98,139,144,162,193],"importance":[31,99,114,145],"estimation":[32,100],"is":[33],"because":[35],"it":[36],"helps":[37],"identify":[38],"the":[39,86,165],"most":[40],"useful":[41],"subsets":[43],"from":[44],"thousands":[45],"of":[46,88],"candidates":[48],"services.":[51],"Such":[52],"selection":[53,65,140,194],"enables":[54],"improved":[55],"performance":[57],"while":[58],"reducing":[59],"computational":[60],"cost.":[61],"To":[62,128],"address":[63,153],"problems":[66],"in":[67,81],"deep":[68],"learning,":[69],"trainable":[70],"gate-based":[71],"sensitivity-based":[73],"methods":[74],"have":[75],"been":[76],"proposed":[77],"proven":[79],"effective":[80],"practice.":[83],"However,":[84],"through":[85],"analysis":[87],"real-world":[89],"cases,":[90],"we":[91,132],"identified":[92],"three":[93],"bias":[94],"issues":[95],"that":[96,184],"cause":[97],"to":[101,112,118,152,164,175],"rely":[102],"on":[103],"partial":[104],"model":[105],"layers,":[106],"samples,":[107],"or":[108],"gradients,":[109],"ultimately":[110],"leading":[111],"inaccurate":[113],"estimation.":[115],"We":[116],"refer":[117],"these":[119,130,188],"layer":[121,154],"bias,":[122,124],"baseline":[123,161,177],"approximation":[126,173,179],"bias.":[127,155],"mitigate":[129],"issues,":[131],"propose":[133],"FairFS,":[134],"a":[135,159],"fair":[136],"accurate":[138],"algorithm.":[141],"FairFS":[142,185],"regularizes":[143],"estimated":[146],"across":[147],"all":[148],"nonlinear":[149],"transformation":[150],"layers":[151],"It":[156],"also":[157],"introduces":[158],"smooth":[160],"close":[163],"classifier":[166],"decision":[167],"boundary":[168],"adopts":[170],"an":[171],"aggregated":[172],"method":[174],"alleviate":[176],"biases.":[180],"Extensive":[181],"experiments":[182],"demonstrate":[183],"effectively":[186],"mitigates":[187],"biases":[189],"achieves":[191],"state-of-the-art":[192],"performance.":[195]},"counts_by_year":[],"updated_date":"2026-02-26T06:34:08.959763","created_date":"2026-02-26T00:00:00"}