{"id":"https://openalex.org/W4402156439","doi":"https://doi.org/10.1109/icc51166.2024.10622512","title":"Submodel Partitioning in Hierarchical Federated Learning: Algorithm Design and Convergence Analysis","display_name":"Submodel Partitioning in Hierarchical Federated Learning: Algorithm Design and Convergence Analysis","publication_year":2024,"publication_date":"2024-06-09","ids":{"openalex":"https://openalex.org/W4402156439","doi":"https://doi.org/10.1109/icc51166.2024.10622512"},"language":"en","primary_location":{"id":"doi:10.1109/icc51166.2024.10622512","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icc51166.2024.10622512","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICC 2024 - IEEE International Conference on Communications","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012031491","display_name":"Wenzhi Fang","orcid":"https://orcid.org/0000-0003-3013-8978"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wenzhi Fang","raw_affiliation_strings":["Elmore Family School of Electrical and Computer Engineering, Purdue University"],"affiliations":[{"raw_affiliation_string":"Elmore Family School of Electrical and Computer Engineering, Purdue University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101403023","display_name":"Dong-Jun Han","orcid":"https://orcid.org/0000-0003-2970-7336"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dong-Jun Han","raw_affiliation_strings":["Elmore Family School of Electrical and Computer Engineering, Purdue University"],"affiliations":[{"raw_affiliation_string":"Elmore Family School of Electrical and Computer Engineering, Purdue University","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020399355","display_name":"Christopher G. Brinton","orcid":"https://orcid.org/0000-0003-2771-3521"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Christopher G. Brinton","raw_affiliation_strings":["Elmore Family School of Electrical and Computer Engineering, Purdue University"],"affiliations":[{"raw_affiliation_string":"Elmore Family School of Electrical and Computer Engineering, Purdue University","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5012031491"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4504,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.8476219,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"268","last_page":"273"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":1.0,"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":1.0,"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/T10237","display_name":"Cryptography and Data Security","score":0.9950000047683716,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9926999807357788,"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/computer-science","display_name":"Computer science","score":0.7688891291618347},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.7648187279701233},{"id":"https://openalex.org/keywords/algorithm-design","display_name":"Algorithm design","score":0.5052550435066223},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4592250883579254}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7688891291618347},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.7648187279701233},{"id":"https://openalex.org/C106516650","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm design","level":2,"score":0.5052550435066223},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4592250883579254},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icc51166.2024.10622512","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icc51166.2024.10622512","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICC 2024 - IEEE International Conference on Communications","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G851766737","display_name":null,"funder_award_id":"N000142212305","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G8814990743","display_name":null,"funder_award_id":"CNS-2146171,CPS-2313109","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2963318081","https://openalex.org/W2963819344","https://openalex.org/W3132103835","https://openalex.org/W3212941463","https://openalex.org/W4210542269","https://openalex.org/W4221157221","https://openalex.org/W4226479888","https://openalex.org/W4283314431","https://openalex.org/W4283798991","https://openalex.org/W4286375442","https://openalex.org/W4288110999","https://openalex.org/W4289258965","https://openalex.org/W4382763193","https://openalex.org/W4399168337","https://openalex.org/W6702112450","https://openalex.org/W6728757088","https://openalex.org/W6752191696","https://openalex.org/W6767781694","https://openalex.org/W6783533280","https://openalex.org/W6797735555","https://openalex.org/W6810211474","https://openalex.org/W6854678524"],"related_works":["https://openalex.org/W2393888177","https://openalex.org/W2544423928","https://openalex.org/W2967268719","https://openalex.org/W2115794623","https://openalex.org/W3115392711","https://openalex.org/W2360264381","https://openalex.org/W2067173559","https://openalex.org/W1613730747","https://openalex.org/W2541389358","https://openalex.org/W4318948887"],"abstract_inverted_index":{"Hierarchical":[0],"federated":[1,14],"learning":[2,15],"(HFL)":[3],"has":[4],"demon-strated":[5],"promising":[6],"scalability":[7],"advantages":[8],"over":[9,36],"the":[10,28,81,108,121,125,129,142,157,180],"traditional":[11],"\u201cstar-topology\u201d":[12],"architecture-based":[13],"(FL).":[16],"How-ever,":[17],"HFL":[18],"still":[19],"imposes":[20],"significant":[21],"computation,":[22],"communication,":[23],"and":[24,90,152],"storage":[25],"burdens":[26],"on":[27,156],"edge,":[29],"especially":[30],"when":[31],"training":[32,51,103],"a":[33,53,72,175],"large-scale":[34],"model":[35,76,83],"resource-constrained":[37],"Internet":[38],"of":[39,75,107,132,144,149],"Things":[40],"(IoT)":[41],"devices.":[42],"In":[43],"this":[44],"paper,":[45],"we":[46,79,164],"propose":[47],"hierarchical":[48,64,73],"independent":[49],"submodel":[50],"(HIST),":[52],"new":[54],"FL":[55],"methodology":[56],"that":[57,97,166],"aims":[58],"to":[59,115,170],"address":[60],"these":[61],"issues":[62],"in":[63,87],"settings.":[65],"The":[66],"key":[67],"idea":[68],"behind":[69],"HIST":[70,133,167],"is":[71,100,168],"version":[74],"partitioning,":[77],"where":[78],"partition":[80,106],"global":[82,153],"into":[84],"disjoint":[85],"submodels":[86],"each":[88,98,113],"round,":[89],"distribute":[91],"them":[92],"across":[93],"different":[94],"cells,":[95,150],"so":[96],"cell":[99],"responsible":[101],"for":[102,134],"only":[104],"one":[105],"full":[109],"model.":[110],"This":[111],"enables":[112],"client":[114],"save":[116,171],"computation/storage":[117],"costs":[118,173],"while":[119,178],"alleviating":[120],"communication":[122,172],"loads":[123],"throughout":[124],"hierarchy.":[126],"We":[127],"characterize":[128],"convergence":[130],"behavior":[131],"non-convex":[135],"loss":[136],"functions":[137],"under":[138],"mild":[139],"assumptions,":[140],"showing":[141],"impact":[143],"several":[145],"attributes":[146],"(e.g.,":[147],"number":[148],"local":[151],"aggregation":[154],"frequency)":[155],"performance-efficiency":[158],"tradeoff.":[159],"Finally,":[160],"through":[161],"numerical":[162],"experiments,":[163],"verify":[165],"able":[169],"by":[174],"wide":[176],"margin":[177],"achieving":[179],"same":[181],"target":[182],"testing":[183],"accuracy.":[184]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}