{"id":"https://openalex.org/W7130423291","doi":"https://doi.org/10.48550/arxiv.2602.15380","title":"Fractional-Order Federated Learning","display_name":"Fractional-Order Federated Learning","publication_year":2026,"publication_date":"2026-02-17","ids":{"openalex":"https://openalex.org/W7130423291","doi":"https://doi.org/10.48550/arxiv.2602.15380"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2602.15380","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.15380","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.2602.15380","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126359097","display_name":"Mohammad Partohaghighi","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Partohaghighi, Mohammad","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005703929","display_name":"Roummel F. Marcia","orcid":"https://orcid.org/0000-0001-6838-140X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marcia, Roummel","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100715957","display_name":"YangQuan Chen","orcid":"https://orcid.org/0000-0002-7422-5988"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, YangQuan","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5126359097"],"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":0.9817000031471252,"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":0.9817000031471252,"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/T13918","display_name":"Advanced Data and IoT Technologies","score":0.0017000000225380063,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.0015999999595806003,"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/federated-learning","display_name":"Federated learning","score":0.883400022983551},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6211000084877014},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5756000280380249},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.5370000004768372},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.508899986743927},{"id":"https://openalex.org/keywords/distributed-learning","display_name":"Distributed learning","score":0.4975000023841858},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.43950000405311584},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.41280001401901245}],"concepts":[{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.883400022983551},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.779699981212616},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6211000084877014},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5756000280380249},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.5370000004768372},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.508899986743927},{"id":"https://openalex.org/C2779582901","wikidata":"https://www.wikidata.org/wiki/Q21013010","display_name":"Distributed learning","level":2,"score":0.4975000023841858},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4575999975204468},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.43950000405311584},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.41280001401901245},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.361299991607666},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.33320000767707825},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3158000111579895},{"id":"https://openalex.org/C102634674","wikidata":"https://www.wikidata.org/wiki/Q868473","display_name":"Smoothness","level":2,"score":0.3125999867916107},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.31119999289512634},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.30570000410079956},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29919999837875366},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.29269999265670776},{"id":"https://openalex.org/C157553263","wikidata":"https://www.wikidata.org/wiki/Q5168004","display_name":"Coordinate descent","level":2,"score":0.2897999882698059},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27880001068115234},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.2757999897003174}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2602.15380","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.15380","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.2602.15380","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.15380","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":[0,45],"learning":[1],"(FL)":[2],"allows":[3],"remote":[4],"clients":[5],"to":[6,55,147],"train":[7],"a":[8,39,88,115,148,181],"global":[9],"model":[10],"collaboratively":[11],"while":[12,75],"protecting":[13],"client":[14,82],"privacy.":[15],"Despite":[16],"its":[17],"privacy-preserving":[18],"benefits,":[19],"FL":[20],"has":[21],"significant":[22],"drawbacks,":[23],"including":[24,99],"slow":[25],"convergence,":[26],"high":[27],"communication":[28,70],"cost,":[29],"and":[30,59,72,112,125,135,154,175],"non-independent-and-identically-distributed":[31],"(non-IID)":[32],"data.":[33,83,189],"In":[34],"this":[35],"work,":[36],"we":[37,142],"present":[38],"novel":[40],"FedAvg":[41],"variation":[42],"called":[43],"Fractional-Order":[44,50],"Averaging":[46],"(FOFedAvg),":[47],"which":[48],"incorporates":[49],"Stochastic":[51],"Gradient":[52],"Descent":[53],"(FOSGD)":[54],"capture":[56],"long-range":[57],"relationships":[58],"deeper":[60],"historical":[61],"information.":[62],"By":[63],"introducing":[64],"memory-aware":[65,168],"fractional-order":[66],"updates,":[67],"FOFedAvg":[68,86,121,145],"improves":[69],"efficiency":[71],"accelerates":[73],"convergence":[74,136],"mitigating":[76],"instability":[77],"caused":[78],"by":[79],"heterogeneous,":[80],"non-IID":[81,118],"We":[84],"compare":[85],"against":[87],"broad":[89],"set":[90],"of":[91,117,132,177],"established":[92],"federated":[93,178],"optimization":[94],"algorithms":[95],"on":[96,187],"benchmark":[97],"datasets":[98],"MNIST,":[100],"FEMNIST,":[101],"CIFAR-10,":[102],"CIFAR-100,":[103],"EMNIST,":[104],"the":[105,139,173],"Cleveland":[106],"heart":[107],"disease":[108],"dataset,":[109],"Sent140,":[110],"PneumoniaMNIST,":[111],"Edge-IIoTset.":[113],"Across":[114],"range":[116],"partitioning":[119],"schemes,":[120],"is":[122],"competitive":[123],"with,":[124],"often":[126],"outperforms,":[127],"these":[128,163],"baselines":[129],"in":[130],"terms":[131],"test":[133],"performance":[134],"speed.":[137],"On":[138],"theoretical":[140],"side,":[141],"prove":[143],"that":[144,166],"converges":[146],"stationary":[149],"point":[150],"under":[151],"standard":[152],"smoothness":[153],"bounded-variance":[155],"assumptions":[156],"for":[157],"fractional":[158],"order":[159],"$0<\u03b1\\le":[160],"1$.":[161],"Together,":[162],"results":[164],"show":[165],"fractional-order,":[167],"updates":[169],"can":[170],"substantially":[171],"improve":[172],"robustness":[174],"effectiveness":[176],"learning,":[179],"offering":[180],"practical":[182],"path":[183],"toward":[184],"distributed":[185],"training":[186],"heterogeneous":[188]},"counts_by_year":[],"updated_date":"2026-02-19T06:31:58.851227","created_date":"2026-02-19T00:00:00"}