{"id":"https://openalex.org/W7138620443","doi":"https://doi.org/10.48550/arxiv.2603.14238","title":"Domain-Skewed Federated Learning with Feature Decoupling and Calibration","display_name":"Domain-Skewed Federated Learning with Feature Decoupling and Calibration","publication_year":2026,"publication_date":"2026-03-15","ids":{"openalex":"https://openalex.org/W7138620443","doi":"https://doi.org/10.48550/arxiv.2603.14238"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.14238","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.14238","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.14238","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129742272","display_name":"Huan Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Huan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129724038","display_name":"Jun Shen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shen, Jun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129683183","display_name":"Jun Yan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan, Jun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5039104219","display_name":"Guansong Pang","orcid":"https://orcid.org/0000-0002-9877-2716"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pang, Guansong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.7125999927520752,"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":0.7125999927520752,"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":0.1768999993801117,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.02449999935925007,"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/discriminative-model","display_name":"Discriminative model","score":0.7260000109672546},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7102000117301941},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.623199999332428},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6141999959945679},{"id":"https://openalex.org/keywords/federated-learning","display_name":"Federated learning","score":0.59170001745224},{"id":"https://openalex.org/keywords/skew","display_name":"Skew","score":0.5909000039100647},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.515500009059906},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4625999927520752},{"id":"https://openalex.org/keywords/decoupling","display_name":"Decoupling (probability)","score":0.45239999890327454}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7745000123977661},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7260000109672546},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7102000117301941},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.623199999332428},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6141999959945679},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.59170001745224},{"id":"https://openalex.org/C43711488","wikidata":"https://www.wikidata.org/wiki/Q7534783","display_name":"Skew","level":2,"score":0.5909000039100647},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5185999870300293},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.515500009059906},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4625999927520752},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.45239999890327454},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4481000006198883},{"id":"https://openalex.org/C101814296","wikidata":"https://www.wikidata.org/wiki/Q5439685","display_name":"Feature model","level":3,"score":0.4431999921798706},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.4343000054359436},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4083000123500824},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.3856000006198883},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.3668000102043152},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.35850000381469727},{"id":"https://openalex.org/C122770356","wikidata":"https://www.wikidata.org/wiki/Q1656753","display_name":"Identifiability","level":2,"score":0.3346000015735626},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3192000091075897},{"id":"https://openalex.org/C2983787585","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature matching","level":3,"score":0.3172999918460846},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.3107999861240387},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.3086000084877014},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2962000072002411},{"id":"https://openalex.org/C2780186347","wikidata":"https://www.wikidata.org/wiki/Q11414","display_name":"Subnetwork","level":2,"score":0.27489998936653137},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2718999981880188},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.2696000039577484},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.14238","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.14238","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.14238","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.14238","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"score":0.6696667075157166,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Federated":[0,84],"learning":[1,37],"(FL)":[2],"allows":[3],"distributed":[4],"clients":[5],"to":[6,74,119,146,175],"collaboratively":[7],"train":[8],"a":[9,13,38,77,166],"global":[10,34],"model":[11,35],"in":[12,43,47,61,117],"privacy-preserving":[14],"manner.":[15],"However,":[16],"one":[17],"major":[18],"challenge":[19],"is":[20,59,114,143,173,202],"domain":[21,57],"skew,":[22],"where":[23],"clients'":[24],"data":[25],"originating":[26],"from":[27,36],"diverse":[28],"domains":[29],"may":[30],"hinder":[31],"the":[32,56,62,70,97,121,129,162,170,188,191,195],"aggregated":[33],"consistent":[39,103],"representation":[40],"space,":[41],"resulting":[42],"poor":[44],"generalizable":[45],"ability":[46],"multiple":[48],"domains.":[49,106],"In":[50],"this":[51],"paper,":[52],"we":[53],"argue":[54],"that":[55,160],"skew":[58],"reflected":[60],"domain-specific":[63,98],"biased":[64,99],"features":[65,131,134,150],"of":[66,123,169,190,197],"each":[67,124],"client,":[68],"causing":[69],"local":[71,130,171],"model's":[72],"representations":[73,104],"collapse":[75],"into":[76,132],"narrow":[78],"low-dimensional":[79],"subspace.":[80],"We":[81],"then":[82],"propose":[83],"Feature":[85,111,140],"Decoupling":[86],"and":[87,135,194],"Calibration":[88],"($F^2$DC),":[89],"which":[90],"liberates":[91],"valuable":[92],"class-relevant":[93,158],"information":[94],"by":[95,151],"calibrating":[96],"features,":[100],"enabling":[101],"more":[102],"across":[105],"A":[107,138],"novel":[108],"component,":[109],"Domain":[110,139],"Decoupler":[112],"(DFD),":[113],"first":[115],"introduced":[116],"$F^2$DC":[118,193],"determine":[120],"robustness":[122],"feature":[125],"unit,":[126],"thereby":[127],"separating":[128],"domain-robust":[133,163],"domain-related":[136,149],"features.":[137,164],"Corrector":[141],"(DFC)":[142],"further":[144],"proposed":[145,192],"calibrate":[147],"these":[148],"explicitly":[152],"linking":[153],"discriminative":[154],"signals,":[155],"capturing":[156],"additional":[157],"clues":[159],"complement":[161],"Finally,":[165],"domain-aware":[167],"aggregation":[168],"models":[172],"performed":[174],"promote":[176],"consensus":[177],"among":[178],"clients.":[179],"Empirical":[180],"results":[181],"on":[182],"three":[183],"popular":[184],"multi-domain":[185],"datasets":[186],"demonstrate":[187],"effectiveness":[189],"contributions":[196],"its":[198],"two":[199],"modules.":[200],"Code":[201],"available":[203],"at":[204],"https://github.com/mala-lab/F2DC.":[205]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-03-18T00:00:00"}