{"id":"https://openalex.org/W7123347868","doi":"https://doi.org/10.1109/tetc.2025.3647650","title":"Robust Model Aggregation for Heterogeneous Federated Learning: Analysis and Optimizations","display_name":"Robust Model Aggregation for Heterogeneous Federated Learning: Analysis and Optimizations","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7123347868","doi":"https://doi.org/10.1109/tetc.2025.3647650"},"language":null,"primary_location":{"id":"doi:10.1109/tetc.2025.3647650","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tetc.2025.3647650","pdf_url":null,"source":{"id":"https://openalex.org/S2496326734","display_name":"IEEE Transactions on Emerging Topics in Computing","issn_l":"2168-6750","issn":["2168-6750","2376-4562"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Emerging Topics in Computing","raw_type":"journal-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/A5022887194","display_name":"Yumeng Shao","orcid":"https://orcid.org/0000-0003-4767-5526"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yumeng Shao","raw_affiliation_strings":["School of Electronic and Optical Engineering, Nanjing University of Science and Technology, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic and Optical Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122864104","display_name":"Jun Li","orcid":null},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Li","raw_affiliation_strings":["School of Information Science and Engineering, Southeast University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080171254","display_name":"Long Shi","orcid":"https://orcid.org/0000-0001-6124-5173"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Long Shi","raw_affiliation_strings":["School of Electronic and Optical Engineering, Nanjing University of Science and Technology, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic and Optical Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122874154","display_name":"Kang Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kang Wei","raw_affiliation_strings":["School of Cyber Science and Engineering, Southeast University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"School of Cyber Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122894990","display_name":"Ming Ding","orcid":null},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"government","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ming Ding","raw_affiliation_strings":["Data61, CSIRO, Sydney, NSW, Australia"],"affiliations":[{"raw_affiliation_string":"Data61, CSIRO, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I42894916","https://openalex.org/I1292875679"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121294907","display_name":"Qianmu Li","orcid":null},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qianmu Li","raw_affiliation_strings":["Digital Economy Research Institute, Nanjing University of Science and Technology, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Digital Economy Research Institute, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zengxiang Li","orcid":"https://orcid.org/0000-0002-1462-9905"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3004594783","display_name":"Institute of High Performance Computing","ror":"https://ror.org/02n0ejh50","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3004594783","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zengxiang Li","raw_affiliation_strings":["Institute of High Performance Computing, A*STAR, Singapore"],"affiliations":[{"raw_affiliation_string":"Institute of High Performance Computing, A*STAR, Singapore","institution_ids":["https://openalex.org/I3004594783","https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122894334","display_name":"Wen Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen Chen","raw_affiliation_strings":["Department of Electronic Engineering, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5122884730","display_name":"Shi Jin","orcid":null},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shi Jin","raw_affiliation_strings":["National Mobile Communications Research Laboratory, Southeast University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"National Mobile Communications Research Laboratory, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5022887194"],"corresponding_institution_ids":["https://openalex.org/I36399199"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10629907,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":"1","first_page":"160","last_page":"171"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.7976999878883362,"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":0.7976999878883362,"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":0.022299999371170998,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.020500000566244125,"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/asynchronous-communication","display_name":"Asynchronous communication","score":0.8064000010490417},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7202000021934509},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5708000063896179},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5432999730110168},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.4805000126361847},{"id":"https://openalex.org/keywords/data-aggregator","display_name":"Data aggregator","score":0.3407000005245209},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.30320000648498535},{"id":"https://openalex.org/keywords/symmetric-multiprocessor-system","display_name":"Symmetric multiprocessor system","score":0.2937999963760376}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9017999768257141},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.8064000010490417},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7202000021934509},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5708000063896179},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5432999730110168},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.48890000581741333},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.4805000126361847},{"id":"https://openalex.org/C82578977","wikidata":"https://www.wikidata.org/wiki/Q16773055","display_name":"Data aggregator","level":3,"score":0.3407000005245209},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.30320000648498535},{"id":"https://openalex.org/C172430144","wikidata":"https://www.wikidata.org/wiki/Q17111997","display_name":"Symmetric multiprocessor system","level":2,"score":0.2937999963760376},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.2906000018119812},{"id":"https://openalex.org/C45493050","wikidata":"https://www.wikidata.org/wiki/Q7884934","display_name":"Unified Model","level":2,"score":0.28610000014305115},{"id":"https://openalex.org/C2777851325","wikidata":"https://www.wikidata.org/wiki/Q7094102","display_name":"Online model","level":2,"score":0.2858999967575073},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.2734000086784363},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27300000190734863},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.26579999923706055},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C130120984","wikidata":"https://www.wikidata.org/wiki/Q2835898","display_name":"Distributed algorithm","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.257099986076355},{"id":"https://openalex.org/C2779582901","wikidata":"https://www.wikidata.org/wiki/Q21013010","display_name":"Distributed learning","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.25619998574256897},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tetc.2025.3647650","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tetc.2025.3647650","pdf_url":null,"source":{"id":"https://openalex.org/S2496326734","display_name":"IEEE Transactions on Emerging Topics in Computing","issn_l":"2168-6750","issn":["2168-6750","2376-4562"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Emerging Topics in Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7431747913360596}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2798720628","https://openalex.org/W2900182564","https://openalex.org/W2912213068","https://openalex.org/W2963318081","https://openalex.org/W2969649567","https://openalex.org/W2978709794","https://openalex.org/W2987371559","https://openalex.org/W2998045710","https://openalex.org/W3012143962","https://openalex.org/W3016083407","https://openalex.org/W3025412407","https://openalex.org/W3093755649","https://openalex.org/W3112972317","https://openalex.org/W3122294042","https://openalex.org/W3127938999","https://openalex.org/W3135099698","https://openalex.org/W3135472452","https://openalex.org/W3136022984","https://openalex.org/W3158259100","https://openalex.org/W4210425674","https://openalex.org/W4224995019","https://openalex.org/W4285246867","https://openalex.org/W4293074290","https://openalex.org/W4383754164","https://openalex.org/W4386276152","https://openalex.org/W4386737174","https://openalex.org/W4387353472","https://openalex.org/W4388676528","https://openalex.org/W4388878683"],"related_works":[],"abstract_inverted_index":{"Conventional":[0],"synchronous":[1],"federated":[2],"learning":[3,112,241],"(SFL)":[4],"frameworks":[5],"suffer":[6],"from":[7,96,151],"performance":[8,43,113],"degradation":[9],"in":[10,240],"heterogeneous":[11,82],"systems":[12],"due":[13],"to":[14,40,132,177],"imbalanced":[15],"local":[16,59,149],"data":[17],"size":[18],"and":[19,34,61,71,186,213],"diverse":[20],"computing":[21],"power":[22],"on":[23,121],"the":[24,42,66,91,94,111,122,129,134,178,184,189,193,198,222,227],"client":[25],"side.":[26],"To":[27,109,191],"address":[28],"this":[29,164],"problem,":[30],"asynchronous":[31,47,50],"FL":[32,36],"(AFL)":[33],"semi-asynchronous":[35],"have":[37],"been":[38],"proposed":[39],"recover":[41],"loss":[44,124],"by":[45,65,232],"allowing":[46],"aggregation.":[48],"However,":[49],"aggregation":[51,130,170],"incurs":[52],"a":[53,76,141,159],"new":[54],"problem":[55],"of":[56,68,87,103,114,155,188,195,229],"inconsistency":[57],"between":[58],"updates":[60],"global":[62,123,179],"updates.":[63],"Motivated":[64],"issues":[67],"conventional":[69,230],"SFL":[70,78,231],"AFL,":[72],"we":[73,116,127,139,201],"first":[74],"propose":[75],"time-driven":[77],"(T-SFL)":[79],"framework":[80],"for":[81],"systems.":[83],"The":[84,215],"core":[85],"idea":[86],"T-SFL":[88,196,220],"is":[89],"that":[90,147,167,219],"server":[92],"aggregates":[93],"models":[95,150],"different":[97],"clients,":[98],"each":[99,168],"with":[100,197,221],"varying":[101],"numbers":[102],"iterations,":[104],"at":[105],"regular":[106],"time":[107],"intervals.":[108],"evaluate":[110],"T-SFL,":[115],"provide":[117],"an":[118,236],"upper":[119,136],"bound":[120],"function.":[125],"Further,":[126],"optimize":[128],"weights":[131],"minimize":[133],"developed":[135],"bound.":[137],"Then,":[138],"develop":[140],"discriminative":[142],"model":[143,180],"selection":[144],"(DMS)":[145],"algorithm":[146,165,224],"removes":[148],"clients":[152],"whose":[153],"number":[154],"iterations":[156],"falls":[157],"below":[158],"predetermined":[160],"threshold.":[161],"In":[162],"particular,":[163],"ensures":[166],"client's":[169],"weight":[171],"accurately":[172],"reflects":[173],"its":[174],"true":[175],"contribution":[176],"update,":[181],"thereby":[182],"improving":[183],"efficiency":[185],"robustness":[187],"system.":[190],"validate":[192],"effectiveness":[194],"DMS":[199,223],"algorithm,":[200],"conduct":[202],"extensive":[203],"experiments":[204],"using":[205],"several":[206],"popular":[207],"datasets":[208],"including":[209],"MNIST,":[210],"Cifar-10,":[211],"Fashion-MNIST,":[212],"SVHN.":[214],"experimental":[216],"results":[217],"demonstrate":[218],"can":[225],"reduce":[226],"latency":[228],"50%,":[233],"while":[234],"achieving":[235],"average":[237],"3%":[238],"improvement":[239],"accuracy":[242],"over":[243],"state-of-the-art":[244],"AFL":[245],"algorithms.":[246]},"counts_by_year":[],"updated_date":"2026-03-25T23:56:10.502304","created_date":"2026-01-14T00:00:00"}