{"id":"https://openalex.org/W7204223577","doi":"https://doi.org/10.1109/edge72783.2026.00026","title":"RAD-SFL: Resource-Aware Dynamic Split Federated Learning for Heterogeneous Edge Environments with Non-IID Data","display_name":"RAD-SFL: Resource-Aware Dynamic Split Federated Learning for Heterogeneous Edge Environments with Non-IID Data","publication_year":2026,"publication_date":"2026-07-01","ids":{"openalex":"https://openalex.org/W7204223577","doi":"https://doi.org/10.1109/edge72783.2026.00026"},"language":"en","primary_location":{"id":"doi:10.1109/edge72783.2026.00026","doi":"https://doi.org/10.1109/edge72783.2026.00026","is_oa":false,"landing_page_url":"https://doi.org/10.1109/edge72783.2026.00026","pdf_url":null,"source":{"id":"https://openalex.org/S7407087562","display_name":"IEEE International Conference on Edge Computing and Communications (EDGE)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE International Conference on Edge Computing and Communications (EDGE)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48620/100537","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048883237","display_name":"Aditya Pribadi Kalapaaking","orcid":"https://orcid.org/0000-0001-5796-8344","observed_orcids":["https://orcid.org/0000-0001-5796-8344"]},"institutions":[{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Aditya Pribadi Kalapaaking","raw_affiliation_strings":["RMIT University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RMIT University","institution_ids":["https://openalex.org/I82951845"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001095666","display_name":"Veronika Stephanie","orcid":"https://orcid.org/0000-0003-2439-641X","observed_orcids":["https://orcid.org/0000-0003-2439-641X"]},"institutions":[{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Veronika Stephanie","raw_affiliation_strings":["RMIT University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RMIT University","institution_ids":["https://openalex.org/I82951845"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037161260","display_name":"Eric Samikwa","orcid":"https://orcid.org/0000-0001-8062-5083","observed_orcids":["https://orcid.org/0000-0001-8062-5083"]},"institutions":[{"id":"https://openalex.org/I118564535","display_name":"University of Bern","ror":"https://ror.org/02k7v4d05","country_code":"CH","type":"education","lineage":["https://openalex.org/I118564535"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Eric Samikwa","raw_affiliation_strings":["University of Bern"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Bern","institution_ids":["https://openalex.org/I118564535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123194362","display_name":"Ibrahim Khalil","orcid":"https://orcid.org/0000-0001-5512-114X","observed_orcids":["https://orcid.org/0000-0001-5512-114X"]},"institutions":[{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ibrahim Khalil","raw_affiliation_strings":["RMIT University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RMIT University","institution_ids":["https://openalex.org/I82951845"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087658596","display_name":"Torsten Ingo Braun","orcid":"https://orcid.org/0000-0001-5968-7108","observed_orcids":["https://orcid.org/0000-0001-5968-7108"]},"institutions":[{"id":"https://openalex.org/I118564535","display_name":"University of Bern","ror":"https://ror.org/02k7v4d05","country_code":"CH","type":"education","lineage":["https://openalex.org/I118564535"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Torsten Braun","raw_affiliation_strings":["University of Bern"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Bern","institution_ids":["https://openalex.org/I118564535"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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":0.55821327,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"128","last_page":"137"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9502000212669373,"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":0.9502000212669373,"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":0.04699999839067459,"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/T13038","display_name":"Internet of Things and AI","score":0.00019999999494757503,"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/federated-learning","display_name":"federated learning","score":0.8149999976158142},{"id":"https://openalex.org/keywords/split-federated-learning","display_name":"split federated learning","score":0.7860000133514404},{"id":"https://openalex.org/keywords/edge-computing","display_name":"edge computing","score":0.8529999852180481},{"id":"https://openalex.org/keywords/non-iid-data","display_name":"non-IID data","score":0.8769999742507935},{"id":"https://openalex.org/keywords/device-heterogeneity","display_name":"heterogeneous devices","score":0.5820000171661377},{"id":"https://openalex.org/keywords/dynamic-resource-allocation","display_name":"dynamic resource allocation","score":0.5870000123977661},{"id":"https://openalex.org/keywords/straggler-mitigation","display_name":"straggler mitigation","score":0.6570000052452087},{"id":"https://openalex.org/keywords/iot-devices","display_name":"IoT devices","score":0.6230000257492065},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"energy consumption","score":0.6869999766349792},{"id":"https://openalex.org/keywords/convergence-rate","display_name":"convergence rate","score":0.4749999940395355}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7028999924659729},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.38519999384880066},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3783999979496002},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.32749998569488525},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3118000030517578},{"id":"https://openalex.org/C20136886","wikidata":"https://www.wikidata.org/wiki/Q749647","display_name":"Interoperability","level":2,"score":0.2888999879360199},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.28630000352859497},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.2838999927043915},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2816999852657318},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2806999981403351},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26840001344680786},{"id":"https://openalex.org/C70061542","wikidata":"https://www.wikidata.org/wiki/Q989016","display_name":"Distributed database","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2651999890804291},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/edge72783.2026.00026","doi":"https://doi.org/10.1109/edge72783.2026.00026","is_oa":false,"landing_page_url":"https://doi.org/10.1109/edge72783.2026.00026","pdf_url":null,"source":{"id":"https://openalex.org/S7407087562","display_name":"IEEE International Conference on Edge Computing and Communications (EDGE)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE International Conference on Edge Computing and Communications (EDGE)","raw_type":"proceedings-article"},{"id":"doi:10.48620/100537","doi":"https://doi.org/10.48620/100537","is_oa":true,"landing_page_url":"https://doi.org/10.48620/100537","pdf_url":null,"source":{"id":"https://openalex.org/S7407053152","display_name":"Open Access CRIS of the University of Bern","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"ConferencePaper"}],"best_oa_location":{"id":"doi:10.48620/100537","doi":"https://doi.org/10.48620/100537","is_oa":true,"landing_page_url":"https://doi.org/10.48620/100537","pdf_url":null,"source":{"id":"https://openalex.org/S7407053152","display_name":"Open Access CRIS of the University of Bern","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"ConferencePaper"},"sustainable_development_goals":[{"score":0.4943999946117401,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W2112796928","https://openalex.org/W2194775991","https://openalex.org/W2734358244","https://openalex.org/W2803823081","https://openalex.org/W2996075766","https://openalex.org/W2998045710","https://openalex.org/W3018102029","https://openalex.org/W3019609389","https://openalex.org/W3047304572","https://openalex.org/W3085873903","https://openalex.org/W3101073882","https://openalex.org/W3102626224","https://openalex.org/W3113772021","https://openalex.org/W3118782137","https://openalex.org/W3134255974","https://openalex.org/W3135231128","https://openalex.org/W3135347465","https://openalex.org/W3137762252","https://openalex.org/W3155912831","https://openalex.org/W3160260334","https://openalex.org/W3196371845","https://openalex.org/W4229029907","https://openalex.org/W4285174182","https://openalex.org/W4285242894","https://openalex.org/W4287332481","https://openalex.org/W4296982580","https://openalex.org/W4309080560","https://openalex.org/W4319663761","https://openalex.org/W4362513799","https://openalex.org/W4377969125","https://openalex.org/W4385236728","https://openalex.org/W4386275757","https://openalex.org/W4386453702","https://openalex.org/W4386702712","https://openalex.org/W4386766757","https://openalex.org/W4394585960","https://openalex.org/W4396782848","https://openalex.org/W4399344896","https://openalex.org/W4399666159"],"related_works":["https://openalex.org/W7128791484","https://openalex.org/W4415209287","https://openalex.org/W4399344896","https://openalex.org/W4414767448","https://openalex.org/W7213411549","https://openalex.org/W7135051339","https://openalex.org/W4411406728","https://openalex.org/W4402676749","https://openalex.org/W6998532107","https://openalex.org/W7212129701"],"abstract_inverted_index":{"Edge":[0],"computing":[1],"enables":[2],"distributed":[3,49],"intelligence":[4],"in":[5,27,51],"resource-constrained":[6],"IoT":[7,122],"environments.":[8,54],"However,":[9],"traditional":[10],"Federated":[11,42],"Learning":[12,43],"(FL)":[13],"struggles":[14],"with":[15,91,120],"heterogeneous":[16,52,121],"device":[17],"capabilities,":[18],"dynamic":[19,58],"network":[20],"conditions,":[21,80],"and":[22,32,71,78,81,116,142,154],"non-IID":[23,100],"data":[24,93],"distributions,":[25],"resulting":[26],"straggler":[28],"effects,":[29],"slow":[30],"convergence,":[31],"inefficient":[33],"resource":[34],"utilization.":[35],"This":[36],"paper":[37],"proposes":[38],"Resource-Aware":[39],"Dynamic":[40],"Split":[41],"(RAD-SFL),":[44],"a":[45,57,82,113,117],"framework":[46],"for":[47],"efficient":[48],"training":[50,130],"edge":[53,72],"RAD-SFL":[55,104,127],"introduces":[56],"model":[59,66,97,145],"layer":[60],"splitting":[61],"mechanism":[62],"that":[63,85,126],"adaptively":[64],"partitions":[65],"execution":[67],"between":[68],"client":[69],"devices":[70,87],"servers":[73],"based":[74],"on":[75,107],"real-time":[76],"computation":[77],"communication":[79],"group-and-reorder":[83],"technique":[84],"organizes":[86],"into":[88],"balanced":[89],"groups":[90],"similar":[92],"distributions":[94],"to":[95,134,149,152],"improve":[96],"convergence":[98],"under":[99],"settings.":[101],"We":[102],"validate":[103],"through":[105],"experiments":[106],"widely":[108],"adopted":[109],"datasets":[110],"using":[111],"both":[112],"simulated":[114],"environment":[115],"real":[118],"testbed":[119],"devices.":[123],"Results":[124],"demonstrate":[125],"reduces":[128],"the":[129],"time":[131],"by":[132,140,147],"up":[133,148],"66.4%,":[135],"decreases":[136],"device-side":[137],"energy":[138],"consumption":[139],"52.5%,":[141],"improves":[143],"global":[144],"accuracy":[146],"30.5%":[150],"compared":[151],"FL":[153],"SFL":[155],"baselines.":[156]},"counts_by_year":[],"updated_date":"2026-10-06T10:28:23.643775","created_date":"2026-08-27T00:00:00"}