{"id":"https://openalex.org/W7131658857","doi":"https://doi.org/10.48550/arxiv.2602.21399","title":"FedVG: Gradient-Guided Aggregation for Enhanced Federated Learning","display_name":"FedVG: Gradient-Guided Aggregation for Enhanced Federated Learning","publication_year":2026,"publication_date":"2026-02-24","ids":{"openalex":"https://openalex.org/W7131658857","doi":"https://doi.org/10.48550/arxiv.2602.21399"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2602.21399","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093081244","display_name":"Alina Devkota","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Devkota, Alina","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072112638","display_name":"Jacob Thrasher","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thrasher, Jacob","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085141731","display_name":"Donald Adjeroh","orcid":"https://orcid.org/0000-0002-7982-4744"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Adjeroh, Donald","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126934414","display_name":"Binod Bhattarai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bhattarai, Binod","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5008803380","display_name":"Prashnna Gyawali","orcid":"https://orcid.org/0000-0003-1201-6993"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gyawali, Prashnna K.","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":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23929571,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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":0.552299976348877,"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":0.552299976348877,"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":0.18119999766349792,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.060499999672174454,"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/benchmarking","display_name":"Benchmarking","score":0.7577000260353088},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6682000160217285},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.6331999897956848},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6075999736785889},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5789999961853027},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5224999785423279},{"id":"https://openalex.org/keywords/federated-learning","display_name":"Federated learning","score":0.5188000202178955},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4302999973297119}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8199999928474426},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.7577000260353088},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6682000160217285},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.6331999897956848},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6075999736785889},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5789999961853027},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5224999785423279},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.5188000202178955},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4302999973297119},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4129999876022339},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.3788999915122986},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3671000003814697},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3610999882221222},{"id":"https://openalex.org/C2779965156","wikidata":"https://www.wikidata.org/wiki/Q5227350","display_name":"Data sharing","level":3,"score":0.34769999980926514},{"id":"https://openalex.org/C82578977","wikidata":"https://www.wikidata.org/wiki/Q16773055","display_name":"Data aggregator","level":3,"score":0.3319000005722046},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.33169999718666077},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3237000107765198},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2980000078678131},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.29260000586509705},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.290800005197525},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.26840001344680786},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2572000026702881},{"id":"https://openalex.org/C184356942","wikidata":"https://www.wikidata.org/wiki/Q830382","display_name":"Best practice","level":2,"score":0.25679999589920044},{"id":"https://openalex.org/C77019957","wikidata":"https://www.wikidata.org/wiki/Q2689057","display_name":"Dependability","level":2,"score":0.25540000200271606}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2602.21399","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2602.21399","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.21399","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":"Preprint"}],"best_oa_location":{"id":"pmh:doi:10.48550/arxiv.2602.21399","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals","score":0.468973308801651}],"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],"Learning":[1],"(FL)":[2],"enables":[3],"collaborative":[4],"model":[5,165],"training":[6],"across":[7,18,85,115,163],"multiple":[8],"clients":[9,19,86],"without":[10,87],"sharing":[11],"their":[12,195],"private":[13],"data.":[14],"However,":[15],"data":[16],"heterogeneity":[17],"leads":[20],"to":[21,63,92,123,135],"client":[22,97,106,133],"drift,":[23],"which":[24],"degrades":[25],"the":[26,31,65,102,110,141],"overall":[27],"generalization":[28,103,139],"performance":[29],"of":[30,105,112],"model.":[32],"This":[33],"effect":[34],"is":[35,180,199],"further":[36,193],"compounded":[37],"by":[38,108],"overemphasis":[39],"on":[40,140,155],"poorly":[41],"performing":[42],"clients.":[43],"To":[44],"address":[45],"this":[46],"problem,":[47],"we":[48,118],"propose":[49],"FedVG,":[50],"a":[51,59,69,125],"novel":[52],"gradient-based":[53],"federated":[54,151],"aggregation":[55],"framework":[56],"that":[57,95,128,168],"leverages":[58],"global":[60,70,142],"validation":[61,71,113,143],"set":[62,72],"guide":[64],"optimization":[66],"process.":[67],"Such":[68],"can":[73,183],"be":[74,184],"established":[75],"using":[76],"readily":[77],"available":[78,200],"public":[79],"datasets,":[80,162],"ensuring":[81],"accessibility":[82],"and":[83,149,158,182],"consistency":[84],"compromising":[88],"privacy.":[89],"In":[90],"contrast":[91],"conventional":[93],"approaches":[94],"prioritize":[96],"dataset":[98],"volume,":[99],"FedVG":[100,169,179],"assesses":[101],"ability":[104],"models":[107],"measuring":[109],"magnitude":[111],"gradients":[114],"layers.":[116],"Specifically,":[117],"compute":[119],"layerwise":[120],"gradient":[121],"norms":[122],"derive":[124],"client-specific":[126],"score":[127],"reflects":[129],"how":[130],"much":[131],"each":[132],"needs":[134],"adjust":[136],"for":[137],"improved":[138],"set,":[144],"thereby":[145],"enabling":[146],"more":[147],"informed":[148],"adaptive":[150],"aggregation.":[152],"Extensive":[153],"experiments":[154],"both":[156],"natural":[157],"medical":[159],"image":[160],"benchmarking":[161],"diverse":[164],"architectures,":[166],"demonstrate":[167],"consistently":[170],"improves":[171],"performance,":[172],"particularly":[173],"in":[174],"highly":[175],"heterogeneous":[176],"settings.":[177],"Moreover,":[178],"modular":[181],"seamlessly":[185],"integrated":[186],"with":[187],"various":[188],"state-of-the-art":[189],"FL":[190],"algorithms,":[191],"often":[192],"improving":[194],"results.":[196],"Our":[197],"code":[198],"at":[201],"https://github.com/alinadevkota/FedVG.":[202]},"counts_by_year":[],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2026-02-27T00:00:00"}