{"id":"https://openalex.org/W7164164479","doi":"https://doi.org/10.48550/arxiv.2606.09869","title":"QSplitFL: Capability Aware Deep Q-Learning for Optimal Split Point Selection in Split Federated Learning","display_name":"QSplitFL: Capability Aware Deep Q-Learning for Optimal Split Point Selection in Split Federated Learning","publication_year":2026,"publication_date":"2026-06-01","ids":{"openalex":"https://openalex.org/W7164164479","doi":"https://doi.org/10.48550/arxiv.2606.09869"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.09869","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.09869","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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.2606.09869","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082224279","display_name":"Nazmus Shakib Shadin","orcid":"https://orcid.org/0000-0002-0999-924X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shadin, Nazmus Shakib","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138325197","display_name":"Xinyue Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Xinyue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138379344","display_name":"Jingyi Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Jingyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138371678","display_name":"Miao Pan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pan, Miao","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":0.9172999858856201,"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":0.9172999858856201,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.015799999237060547,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T14347","display_name":"Big Data and Digital Economy","score":0.006899999920278788,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/convergence","display_name":"Convergence (economics)","score":0.52920001745224},{"id":"https://openalex.org/keywords/federated-learning","display_name":"Federated learning","score":0.508400022983551},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.48980000615119934},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4869999885559082},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.45899999141693115},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4580000042915344},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4302999973297119},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.42899999022483826},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.4083999991416931}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8460000157356262},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5447999835014343},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.52920001745224},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.508400022983551},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.48980000615119934},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4869999885559082},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.45899999141693115},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4580000042915344},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4302999973297119},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42910000681877136},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.42899999022483826},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4083999991416931},{"id":"https://openalex.org/C2779582901","wikidata":"https://www.wikidata.org/wiki/Q21013010","display_name":"Distributed learning","level":2,"score":0.40529999136924744},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.38960000872612},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3635999858379364},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.36059999465942383},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3499000072479248},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.31769999861717224},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.3082999885082245},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.30820000171661377},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.303600013256073},{"id":"https://openalex.org/C2775973920","wikidata":"https://www.wikidata.org/wiki/Q3252726","display_name":"Selection algorithm","level":3,"score":0.3019999861717224},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.2989000082015991},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2962000072002411},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.29589998722076416},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.26489999890327454},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.257999986410141},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.2574999928474426},{"id":"https://openalex.org/C520049643","wikidata":"https://www.wikidata.org/wiki/Q189760","display_name":"Voting","level":3,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.09869","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.09869","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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.2606.09869","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.09869","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Federated":[0,95],"Learning":[1,6,96],"(FL)":[2],"combined":[3],"with":[4,148],"Split":[5,92],"(SL)":[7],"is":[8,41,195],"a":[9,45,79,111,134,144],"privacy":[10],"preserving":[11],"paradigm":[12],"that":[13,102,139,172],"enables":[14],"training":[15,27],"deep":[16],"neural":[17],"networks":[18],"(DNNs)":[19],"on":[20,104,157],"resource":[21],"constrained":[22],"devices":[23,61],"while":[24,185],"reducing":[25],"overall":[26],"cost.":[28],"However,":[29],"determining":[30],"the":[31,36,39,64],"optimal":[32,87],"split":[33,56,88],"point,":[34],"meaning":[35],"layer":[37],"where":[38],"model":[40,106],"divided":[42],"still":[43],"remains":[44],"critical":[46],"challenge,":[47],"especially":[48],"when":[49],"clients":[50],"have":[51],"heterogeneous":[52,189],"hardware":[53,119],"capabilities.":[54],"Fixed":[55],"points":[57],"can":[58],"overload":[59],"weak":[60],"and":[62,66,72,127,143,161,168,178],"increase":[63],"communication":[65],"server":[67],"load,":[68],"which":[69],"slows":[70],"convergence":[71,177],"reduces":[73],"stability.":[74],"This":[75],"paper":[76],"introduces":[77],"QSplitFL,":[78],"novel":[80],"capability-aware":[81],"Deep":[82],"Q-Network":[83],"(DQN)":[84],"framework":[85,132],"for":[86],"point":[89],"selection":[90],"in":[91],"learning":[93],"based":[94],"(SFL)":[97],"environments.":[98],"Unlike":[99],"existing":[100,183],"approaches":[101],"rely":[103],"high-dimensional":[105],"weight":[107],"representations,":[108],"QSplitFL":[109],"employs":[110],"lightweight":[112],"state":[113],"representation":[114],"derived":[115],"directly":[116],"from":[117],"client":[118],"metrics,":[120],"including":[121],"CPU":[122],"utilization,":[123],"memory,":[124],"battery":[125],"level,":[126],"network":[128],"latency.":[129],"The":[130,192],"proposed":[131],"incorporates":[133],"decayed":[135],"loss-drop":[136],"reward":[137,153],"function":[138],"prioritizes":[140],"early":[141],"convergence,":[142],"committee-based":[145],"DQN":[146],"architecture":[147],"majority":[149],"voting":[150],"to":[151,182,188],"mitigate":[152],"hacking.":[154],"Extensive":[155],"experiments":[156],"MNIST,":[158],"Fashion-MNIST,":[159],"CIFAR-10,":[160],"CIFAR-100":[162],"datasets":[163],"using":[164],"CNN,":[165],"ResNet50,":[166],"MobileNetV4,":[167],"ConvNeXt":[169],"architectures":[170],"demonstrate":[171],"our":[173],"approach":[174],"achieves":[175],"better":[176],"higher":[179],"accuracy":[180],"compared":[181],"methods,":[184],"effectively":[186],"adapting":[187],"device":[190],"resources.":[191],"source":[193],"code":[194],"publicly":[196],"available":[197],"at":[198],"https://github.com/AIPO-Lab/QSplitFL.":[199]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-06-11T00:00:00"}