{"id":"https://openalex.org/W7133316817","doi":"https://doi.org/10.48550/arxiv.2603.00579","title":"DeepAFL: Deep Analytic Federated Learning","display_name":"DeepAFL: Deep Analytic Federated Learning","publication_year":2026,"publication_date":"2026-02-28","ids":{"openalex":"https://openalex.org/W7133316817","doi":"https://doi.org/10.48550/arxiv.2603.00579"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.00579","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.00579","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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.00579","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128008079","display_name":"Jianheng Tang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Tang, Jianheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106405880","display_name":"Yajiang Huang","orcid":"https://orcid.org/0009-0006-5023-0738"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Yajiang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127975233","display_name":"Kejia Fan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan, Kejia","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016430981","display_name":"Feijiang Han","orcid":"https://orcid.org/0009-0001-7880-5349"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Han, Feijiang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127944997","display_name":"Jiaxu Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Jiaxu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128031886","display_name":"Jinfeng Xu (5966045)","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Jinfeng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127912189","display_name":"Run He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Run","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075435434","display_name":"Anfeng Liu","orcid":"https://orcid.org/0000-0001-5190-4761"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Anfeng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127941668","display_name":"Houbing Herbert Song","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song, Houbing Herbert","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127923253","display_name":"Huiping Zhuang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhuang, Huiping","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5082653046","display_name":"Yunhuai Liu","orcid":"https://orcid.org/0000-0002-1180-8078"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yunhuai","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5128008079"],"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":0.6926000118255615,"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":0.6926000118255615,"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":0.09470000118017197,"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":0.02319999970495701,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6412000060081482},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6072999835014343},{"id":"https://openalex.org/keywords/protocol","display_name":"Protocol (science)","score":0.5756000280380249},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5618000030517578},{"id":"https://openalex.org/keywords/federated-learning","display_name":"Federated learning","score":0.5177000164985657},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.5077000260353088},{"id":"https://openalex.org/keywords/external-data-representation","display_name":"External Data Representation","score":0.48579999804496765},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.4747999906539917}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7983999848365784},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6412000060081482},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6072999835014343},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5766000151634216},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.5756000280380249},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5618000030517578},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.5177000164985657},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.5077000260353088},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4945000112056732},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.48579999804496765},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.4747999906539917},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3921999931335449},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.3921999931335449},{"id":"https://openalex.org/C2776639384","wikidata":"https://www.wikidata.org/wiki/Q840396","display_name":"Ideal (ethics)","level":2,"score":0.3873000144958496},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.37310001254081726},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3702000081539154},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3479999899864197},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3257000148296356},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3188000023365021},{"id":"https://openalex.org/C2779582901","wikidata":"https://www.wikidata.org/wiki/Q21013010","display_name":"Distributed learning","level":2,"score":0.2802000045776367},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2597000002861023},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2535000145435333},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.00579","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.00579","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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.00579","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.00579","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":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Federated":[0,113],"Learning":[1,114],"(FL)":[2],"is":[3],"a":[4,69,74],"popular":[5],"distributed":[6],"learning":[7,88],"paradigm":[8],"to":[9,38,55,83,93,103,186],"break":[10],"down":[11],"data":[12,56,104],"silo.":[13],"Traditional":[14],"FL":[15,156],"approaches":[16,59],"largely":[17],"rely":[18],"on":[19],"gradient-based":[20,44,127],"updates,":[21],"facing":[22],"significant":[23],"issues":[24,41],"about":[25],"heterogeneity,":[26,57],"scalability,":[27],"convergence,":[28],"and":[29,163,178],"overhead,":[30],"etc.":[31],"Recently,":[32],"some":[33],"analytic-learning-based":[34],"work":[35],"has":[36],"attempted":[37],"handle":[39],"these":[40,58],"by":[42,63,153,184],"eliminating":[43],"updates":[45],"via":[46],"analytical":[47,138],"(i.e.,":[48],"closed-form)":[49],"solutions.":[50,139],"Despite":[51],"achieving":[52],"superior":[53,169],"invariance":[54,102,177],"are":[60],"fundamentally":[61],"limited":[62],"their":[64,84],"single-layer":[65],"linear":[66],"model":[67],"with":[68,137,171],"frozen":[70],"pre-trained":[71],"backbone.":[72],"As":[73],"result,":[75],"they":[76],"can":[77],"only":[78],"achieve":[79],"suboptimal":[80],"performance":[81,170],"due":[82],"lack":[85],"of":[86,124],"representation":[87,179],"capabilities.":[89],"In":[90],"this":[91],"paper,":[92],"enable":[94],"representable":[95],"analytic":[96,150],"models":[97,151],"while":[98],"preserving":[99],"the":[100,121],"ideal":[101],"heterogeneity":[105,176],"for":[106,146],"FL,":[107],"we":[108,129],"propose":[109],"our":[110,135,148,167],"Deep":[111],"Analytic":[112],"approach,":[115],"named":[116],"DeepAFL.":[117],"Drawing":[118],"inspiration":[119],"from":[120],"great":[122],"success":[123],"ResNet":[125],"in":[126,134,155,175],"learning,":[128,180],"design":[130],"gradient-free":[131],"residual":[132],"blocks":[133],"DeepAFL":[136],"We":[140],"introduce":[141],"an":[142],"efficient":[143],"layer-wise":[144],"protocol":[145],"training":[147],"deep":[149],"layer":[152,154],"through":[157],"least":[158],"squares.":[159],"Both":[160],"theoretical":[161],"analyses":[162],"empirical":[164],"evaluations":[165],"validate":[166],"DeepAFL's":[168],"its":[172],"dual":[173],"advantages":[174],"outperforming":[181],"state-of-the-art":[182],"baselines":[183],"up":[185],"5.68%-8.42%":[187],"across":[188],"three":[189],"benchmark":[190],"datasets.":[191]},"counts_by_year":[],"updated_date":"2026-03-04T07:09:34.246503","created_date":"2026-03-04T00:00:00"}