{"id":"https://openalex.org/W7160268482","doi":"https://doi.org/10.1109/wacv61042.2026.00047","title":"AFL-PRF: Adaptive Federated Learning for Low-Quality Data: Enhancing Performance, Robustness, and Fairness","display_name":"AFL-PRF: Adaptive Federated Learning for Low-Quality Data: Enhancing Performance, Robustness, and Fairness","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W7160268482","doi":"https://doi.org/10.1109/wacv61042.2026.00047"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00047","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00047","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-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/A5113306682","display_name":"Pinrui Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I87182695","display_name":"Universidad del Noreste","ror":"https://ror.org/02ahky613","country_code":"MX","type":"education","lineage":["https://openalex.org/I87182695"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Pinrui Yu","raw_affiliation_strings":["Northeastern University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University","institution_ids":["https://openalex.org/I87182695"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102716914","display_name":"Yiming Xie","orcid":"https://orcid.org/0009-0007-8841-9699"},"institutions":[{"id":"https://openalex.org/I87182695","display_name":"Universidad del Noreste","ror":"https://ror.org/02ahky613","country_code":"MX","type":"education","lineage":["https://openalex.org/I87182695"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Yiming Xie","raw_affiliation_strings":["Northeastern University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University","institution_ids":["https://openalex.org/I87182695"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104205155","display_name":"Longtian Ye","orcid":null},"institutions":[{"id":"https://openalex.org/I87182695","display_name":"Universidad del Noreste","ror":"https://ror.org/02ahky613","country_code":"MX","type":"education","lineage":["https://openalex.org/I87182695"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Longtian Ye","raw_affiliation_strings":["Northeastern University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University","institution_ids":["https://openalex.org/I87182695"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135335595","display_name":"Geng Yuan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Geng Yuan","raw_affiliation_strings":["University of Georgia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Georgia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091825452","display_name":"Ningfang Mi","orcid":"https://orcid.org/0009-0005-0934-1287"},"institutions":[{"id":"https://openalex.org/I87182695","display_name":"Universidad del Noreste","ror":"https://ror.org/02ahky613","country_code":"MX","type":"education","lineage":["https://openalex.org/I87182695"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Ningfang Mi","raw_affiliation_strings":["Northeastern University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University","institution_ids":["https://openalex.org/I87182695"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033966600","display_name":"Xue Lin","orcid":"https://orcid.org/0000-0002-9890-7318"},"institutions":[{"id":"https://openalex.org/I87182695","display_name":"Universidad del Noreste","ror":"https://ror.org/02ahky613","country_code":"MX","type":"education","lineage":["https://openalex.org/I87182695"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Xue Lin","raw_affiliation_strings":["Northeastern University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University","institution_ids":["https://openalex.org/I87182695"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.68803132,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"402","last_page":"411"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.7322999835014343,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.7322999835014343,"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/T11719","display_name":"Data Quality and Management","score":0.07720000296831131,"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"}},{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.023800000548362732,"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/key","display_name":"Key (lock)","score":0.3199999928474426},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.3075000047683716},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.28299999237060547},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.2800999879837036},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2694999873638153}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.621399998664856},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3199999928474426},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3075000047683716},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.3028999865055084},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2800999879837036},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.25859999656677246},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.25270000100135803},{"id":"https://openalex.org/C2778137410","wikidata":"https://www.wikidata.org/wiki/Q2732820","display_name":"Government (linguistics)","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv61042.2026.00047","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00047","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2473418344","https://openalex.org/W2774018344","https://openalex.org/W3045674654","https://openalex.org/W3087391814","https://openalex.org/W3109723249","https://openalex.org/W3138597937","https://openalex.org/W3153283578","https://openalex.org/W3204423820","https://openalex.org/W4206320562","https://openalex.org/W4213446860","https://openalex.org/W4221129260","https://openalex.org/W4285722492","https://openalex.org/W4405022503","https://openalex.org/W4406458734","https://openalex.org/W4412955288","https://openalex.org/W4414601526"],"related_works":[],"abstract_inverted_index":{"Federated":[0],"learning":[1,53,154,200],"(FL)":[2],"enables":[3],"collaborative":[4],"model":[5],"training":[6],"across":[7],"distributed":[8],"clients":[9],"while":[10,87,151,179],"preserving":[11,152],"privacy,":[12],"yet":[13],"its":[14],"decentralized":[15],"nature":[16],"makes":[17],"it":[18],"vulnerable":[19,133],"to":[20,135],"poisoned":[21,83,202],"updates":[22,112,147],"and":[23,36,60,64,113,174,190,203],"performance":[24],"degradation":[25],"under":[26,201],"highly":[27,132,204],"skewed":[28],"data.":[29],"Prior":[30],"studies":[31],"typically":[32],"treat":[33],"accuracy,":[34,58],"robustness,":[35,59],"fairness":[37,61],"separately,":[38],"leaving":[39],"open":[40],"the":[41,103],"challenge":[42],"of":[43],"a":[44,97,140,195],"unified":[45],"solution.":[46],"We":[47],"propose":[48],"AFL-PRF,":[49],"an":[50,73],"adaptive":[51,75,186],"federated":[52,199],"framework":[54],"that":[55,144,162],"simultaneously":[56],"enhances":[57],"in":[62,148,172,177],"adversarial":[63],"heterogeneous":[65],"environments.":[66],"AFL-PRF":[67,163,193],"integrates":[68],"three":[69],"key":[70],"techniques.":[71],"First,":[72],"exponential":[74],"weighting":[76],"mechanism":[77],"dynamically":[78],"scales":[79],"client":[80,98,188],"updates,":[81],"suppressing":[82],"or":[84],"unreliable":[85],"contributions":[86],"retaining":[88],"meaningful":[89],"signals":[90],"from":[91,120],"benign":[92,115],"but":[93],"low-quality":[94],"clients.":[95],"Second,":[96],"prioritization":[99],"strategy":[100,143],"guided":[101],"by":[102],"novel":[104],"Weight":[105],"Update":[106],"Divergence":[107],"(WUD)":[108],"score":[109],"promotes":[110],"reliable":[111],"their":[114],"neighbors,":[116],"preventing":[117],"malicious":[118],"gradients":[119],"dominating":[121],"aggregation.":[122],"Third,":[123],"sensitivity":[124],"profiling":[125],"identifies":[126],"fully":[127],"connected":[128],"(FC)":[129],"layers":[130,150],"as":[131],"due":[134],"large":[136],"weight":[137],"variance,":[138],"motivating":[139],"selective":[141],"clipping":[142],"filters":[145],"extreme":[146],"these":[149],"normal":[153],"dynamics.":[155],"Extensive":[156],"experiments":[157],"on":[158],"benchmark":[159,197],"datasets":[160],"demonstrate":[161],"consistently":[164],"outperforms":[165],"state-of-the-art":[166],"baselines,":[167],"achieving":[168],"over":[169],"30%":[170],"improvement":[171],"robustness":[173],"20%":[175],"enhancement":[176],"fairness,":[178],"maintaining":[180],"superior":[181],"predictive":[182],"accuracy.":[183],"By":[184],"unifying":[185],"weighting,":[187],"prioritization,":[189],"targeted":[191],"clipping,":[192],"establishes":[194],"new":[196],"for":[198],"non-IID":[205],"conditions.":[206]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-06T00:00:00"}