{"id":"https://openalex.org/W4406458147","doi":"https://doi.org/10.1109/bigdata62323.2024.10826106","title":"FedISMH: Federated Learning Via Inference Similarity for Model Heterogeneous","display_name":"FedISMH: Federated Learning Via Inference Similarity for Model Heterogeneous","publication_year":2024,"publication_date":"2024-12-15","ids":{"openalex":"https://openalex.org/W4406458147","doi":"https://doi.org/10.1109/bigdata62323.2024.10826106"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata62323.2024.10826106","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10826106","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","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/A5014965312","display_name":"Yongdong Li","orcid":"https://orcid.org/0000-0001-8756-0438"},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yongdong Li","raw_affiliation_strings":["Guangxi Normal University,School of Computer Science and Engineering,Guilin,China"],"affiliations":[{"raw_affiliation_string":"Guangxi Normal University,School of Computer Science and Engineering,Guilin,China","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100744940","display_name":"Li-e Wang","orcid":"https://orcid.org/0000-0002-1966-3045"},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li-e Wang","raw_affiliation_strings":["Guangxi Normal University,School of Computer Science and Engineering,Guilin,China"],"affiliations":[{"raw_affiliation_string":"Guangxi Normal University,School of Computer Science and Engineering,Guilin,China","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058071048","display_name":"Zhigang Sun","orcid":"https://orcid.org/0000-0003-1705-1165"},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhigang Sun","raw_affiliation_strings":["Guangxi Normal University,School of Computer Science and Engineering,Guilin,China"],"affiliations":[{"raw_affiliation_string":"Guangxi Normal University,School of Computer Science and Engineering,Guilin,China","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037037839","display_name":"Xianxian Li","orcid":"https://orcid.org/0000-0002-7083-3847"},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianxian Li","raw_affiliation_strings":["Guangxi Normal University,School of Computer Science and Engineering,Guilin,China"],"affiliations":[{"raw_affiliation_string":"Guangxi Normal University,School of Computer Science and Engineering,Guilin,China","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114189293","display_name":"Hengtong Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hengtong Chang","raw_affiliation_strings":["Guangxi Normal University,School of Computer Science and Engineering,Guilin,China"],"affiliations":[{"raw_affiliation_string":"Guangxi Normal University,School of Computer Science and Engineering,Guilin,China","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102335896","display_name":"Jinke Xu","orcid":"https://orcid.org/0009-0007-1441-7666"},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinke Xu","raw_affiliation_strings":["Guangxi Normal University,School of Computer Science and Engineering,Guilin,China"],"affiliations":[{"raw_affiliation_string":"Guangxi Normal University,School of Computer Science and Engineering,Guilin,China","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103188332","display_name":"Chin-Cheng Lin","orcid":"https://orcid.org/0000-0003-0566-0190"},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Caiyi Lin","raw_affiliation_strings":["Guangxi Normal University,School of Computer Science and Engineering,Guilin,China"],"affiliations":[{"raw_affiliation_string":"Guangxi Normal University,School of Computer Science and Engineering,Guilin,China","institution_ids":["https://openalex.org/I29739308"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5014965312"],"corresponding_institution_ids":["https://openalex.org/I29739308"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23719144,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7909","last_page":"7918"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9891999959945679,"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/T11719","display_name":"Data Quality and Management","score":0.9828000068664551,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7739090919494629},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7580323219299316},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6500464677810669},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5015819072723389},{"id":"https://openalex.org/keywords/federated-learning","display_name":"Federated learning","score":0.443036288022995},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37593019008636475}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7739090919494629},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7580323219299316},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6500464677810669},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5015819072723389},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.443036288022995},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37593019008636475},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata62323.2024.10826106","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10826106","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320325559","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W2035890032","https://openalex.org/W2807006176","https://openalex.org/W2900120080","https://openalex.org/W2942810103","https://openalex.org/W2963819344","https://openalex.org/W2995022099","https://openalex.org/W3035453001","https://openalex.org/W3038028469","https://openalex.org/W3091870957","https://openalex.org/W3099314130","https://openalex.org/W3156467244","https://openalex.org/W3169044395","https://openalex.org/W3192098883","https://openalex.org/W4226297372","https://openalex.org/W4230575913","https://openalex.org/W4285762978","https://openalex.org/W4300427714","https://openalex.org/W4304080258","https://openalex.org/W4312231739","https://openalex.org/W4312699393","https://openalex.org/W4365511397","https://openalex.org/W4386044362","https://openalex.org/W4386608426","https://openalex.org/W4387969057","https://openalex.org/W4389252625","https://openalex.org/W4393156437","https://openalex.org/W4400489144","https://openalex.org/W4403582721","https://openalex.org/W6637131181","https://openalex.org/W6728757088","https://openalex.org/W6738383168","https://openalex.org/W6752029299","https://openalex.org/W6755988804","https://openalex.org/W6759226220","https://openalex.org/W6759238902","https://openalex.org/W6761472960","https://openalex.org/W6773817997","https://openalex.org/W6779174293","https://openalex.org/W6780224944","https://openalex.org/W6784336702","https://openalex.org/W6791102956","https://openalex.org/W6839303856","https://openalex.org/W6855922729"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W3046775127","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474"],"abstract_inverted_index":{"Federated":[0],"Learning":[1],"(FL)":[2],"is":[3],"a":[4,50,107],"privacy-preserving":[5],"machine":[6],"learning":[7],"paradigm,":[8],"enabling":[9],"decentralized":[10],"devices":[11],"to":[12,53,94,110],"collaboratively":[13],"train":[14],"models":[15],"without":[16],"sharing":[17],"local":[18],"data.":[19],"Traditional":[20],"FL":[21,160],"approaches,":[22],"however,":[23],"rely":[24],"on":[25,69,135],"averaging":[26],"parameters":[27],"across":[28],"clients":[29,40,67,96,113],"with":[30,97,117],"homogeneous":[31],"models,":[32,75],"which":[33],"limits":[34],"their":[35,125],"applicability":[36],"in":[37,57,146,158],"scenarios":[38],"where":[39,76],"require":[41],"heterogeneous":[42,159],"models.":[43],"In":[44],"this":[45],"paper,":[46],"we":[47],"propose":[48],"FedISMH,":[49],"novel":[51],"approach":[52],"address":[54],"model":[55,93,99],"heterogeneity":[56],"FL.":[58],"Instead":[59],"of":[60,73,130],"directly":[61],"applying":[62],"knowledge":[63],"distillation,":[64],"FedISMH":[65,105,141],"clusters":[66],"based":[68],"the":[70,91,118,128,131],"structural":[71,78],"similarities":[72],"client":[74],"clients\u2019":[77],"features":[79],"can":[80],"be":[81],"extracted":[82],"through":[83],"either":[84],"labeled":[85],"or":[86],"unlabeled":[87],"dataset":[88],"This":[89],"allows":[90],"proposed":[92],"identify":[95],"similar":[98,121],"architectures":[100],"while":[101],"preserving":[102],"privacy.":[103],"Additionally,":[104],"introduces":[106],"dynamic":[108],"mechanism":[109],"manage":[111],"noise":[112],"by":[114],"aligning":[115],"them":[116],"most":[119],"structurally":[120],"clusters,":[122],"ensuring":[123],"that":[124,140],"inclusion":[126],"promote":[127],"performance":[129],"cluster.":[132],"Experimental":[133],"results":[134],"MNIST":[136],"and":[137,149,156],"SVHN":[138],"demonstrate":[139],"consistently":[142],"outperforms":[143],"state-of-the-art":[144],"methods":[145],"both":[147],"IID":[148],"Non-IID":[150],"settings,":[151],"offering":[152],"improved":[153],"accuracy,":[154],"robustness,":[155],"flexibility":[157],"environments.":[161]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}