{"id":"https://openalex.org/W4285601829","doi":"https://doi.org/10.24963/ijcai.2022/399","title":"Heterogeneous Ensemble Knowledge Transfer for Training Large Models in Federated Learning","display_name":"Heterogeneous Ensemble Knowledge Transfer for Training Large Models in Federated Learning","publication_year":2022,"publication_date":"2022-07-01","ids":{"openalex":"https://openalex.org/W4285601829","doi":"https://doi.org/10.24963/ijcai.2022/399"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2022/399","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/399","pdf_url":"https://www.ijcai.org/proceedings/2022/0399.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.ijcai.org/proceedings/2022/0399.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025202888","display_name":"Yae Jee Cho","orcid":"https://orcid.org/0000-0001-6075-2712"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["GB","US"],"is_corresponding":true,"raw_author_name":"Yae Jee Cho","raw_affiliation_strings":["Carnegie Mellon University","Microsoft Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023529203","display_name":"Andre Manoel","orcid":"https://orcid.org/0000-0002-5455-0230"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Andre Manoel","raw_affiliation_strings":["Microsoft Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000950022","display_name":"Gauri Joshi","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gauri Joshi","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090308773","display_name":"Robert B. Sim","orcid":"https://orcid.org/0000-0002-2855-7455"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Robert Sim","raw_affiliation_strings":["Microsoft Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5115044944","display_name":"Dimitrios Dimitriadis","orcid":"https://orcid.org/0000-0001-8483-0105"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Dimitrios Dimitriadis","raw_affiliation_strings":["Microsoft Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5025202888"],"corresponding_institution_ids":["https://openalex.org/I4210164937","https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":9.5673,"has_fulltext":true,"cited_by_count":100,"citation_normalized_percentile":{"value":0.98706942,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2881","last_page":"2887"},"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9670000076293945,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9660000205039978,"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":0.8141244053840637},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"Ensemble learning","score":0.7952810525894165},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5821895003318787},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5792456269264221},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5220960378646851},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5162336826324463},{"id":"https://openalex.org/keywords/federated-learning","display_name":"Federated learning","score":0.5148472189903259},{"id":"https://openalex.org/keywords/intuition","display_name":"Intuition","score":0.5146723389625549},{"id":"https://openalex.org/keywords/ensemble-forecasting","display_name":"Ensemble forecasting","score":0.5004293918609619},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.46188777685165405},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.44901415705680847},{"id":"https://openalex.org/keywords/multiple-models","display_name":"Multiple Models","score":0.4397997558116913},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.4224083125591278}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8141244053840637},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.7952810525894165},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5821895003318787},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5792456269264221},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5220960378646851},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5162336826324463},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.5148472189903259},{"id":"https://openalex.org/C132010649","wikidata":"https://www.wikidata.org/wiki/Q189222","display_name":"Intuition","level":2,"score":0.5146723389625549},{"id":"https://openalex.org/C119898033","wikidata":"https://www.wikidata.org/wiki/Q3433888","display_name":"Ensemble forecasting","level":2,"score":0.5004293918609619},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.46188777685165405},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.44901415705680847},{"id":"https://openalex.org/C2779714256","wikidata":"https://www.wikidata.org/wiki/Q25305062","display_name":"Multiple Models","level":2,"score":0.4397997558116913},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.4224083125591278},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2022/399","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/399","pdf_url":"https://www.ijcai.org/proceedings/2022/0399.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2022/399","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/399","pdf_url":"https://www.ijcai.org/proceedings/2022/0399.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4285601829.pdf","grobid_xml":"https://content.openalex.org/works/W4285601829.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1821462560","https://openalex.org/W2194775991","https://openalex.org/W2541884796","https://openalex.org/W2807912816","https://openalex.org/W2913570153","https://openalex.org/W2914328083","https://openalex.org/W2972570881","https://openalex.org/W2981206218","https://openalex.org/W3000462134","https://openalex.org/W3004309231","https://openalex.org/W3035453001","https://openalex.org/W3038022836","https://openalex.org/W3038028469","https://openalex.org/W3094163844","https://openalex.org/W3113303810","https://openalex.org/W3141518839","https://openalex.org/W3161687676","https://openalex.org/W3178336997","https://openalex.org/W3183771526","https://openalex.org/W3201527618","https://openalex.org/W3202213872","https://openalex.org/W3202586005","https://openalex.org/W3206466389","https://openalex.org/W4287064345","https://openalex.org/W4294106961","https://openalex.org/W4318619660","https://openalex.org/W6752186649","https://openalex.org/W6783655119","https://openalex.org/W6803771590","https://openalex.org/W6864014924"],"related_works":["https://openalex.org/W2794896638","https://openalex.org/W2891633941","https://openalex.org/W3202800081","https://openalex.org/W3101614107","https://openalex.org/W4390971112","https://openalex.org/W3036530763","https://openalex.org/W4383368890","https://openalex.org/W1909207154","https://openalex.org/W2201958145","https://openalex.org/W3176003670"],"abstract_inverted_index":{"Federated":[0],"learning":[1],"(FL)":[2],"enables":[3],"edge-devices":[4],"to":[5,15,29,40,45,76],"collaboratively":[6],"learn":[7],"a":[8,16,55,78,107],"model":[9,80],"without":[10],"disclosing":[11],"their":[12],"private":[13],"data":[14],"central":[17],"aggregating":[18],"server.":[19,83],"Most":[20],"existing":[21],"FL":[22,90,168],"algorithms":[23,169],"require":[24],"models":[25,43,66,143],"of":[26,102,141,152],"identical":[27],"architecture":[28],"be":[30,94],"deployed":[31],"across":[32],"the":[33,82,91,121,128,131,135,139,150],"clients":[34],"and":[35,74,158,174],"server,":[36],"making":[37],"it":[38],"infeasible":[39],"train":[41,77],"large":[42],"due":[44],"clients'":[46,97],"limited":[47],"system":[48],"resources.":[49],"In":[50],"this":[51,103],"work,":[52],"we":[53],"propose":[54],"novel":[56],"ensemble":[57,87,92,122,140],"knowledge":[58],"transfer":[59],"method":[60],"named":[61],"Fed-ET":[62,105,163],"in":[63,68,85,89],"which":[64],"small":[65],"(different":[67],"architecture)":[69],"are":[70],"trained":[71,95,144],"on":[72,96,145,156],"clients,":[73],"used":[75],"larger":[79],"at":[81],"Unlike":[84],"conventional":[86],"learning,":[88],"can":[93],"highly":[98],"heterogeneous":[99,146],"data.":[100],"Cognizant":[101],"property,":[104],"uses":[106],"weighted":[108,142],"consensus":[109,119],"distillation":[110],"scheme":[111],"with":[112,170],"diversity":[113,129],"regularization":[114],"that":[115,148,162],"efficiently":[116],"extracts":[117],"reliable":[118],"from":[120],"while":[123],"improving":[124],"generalization":[125,136],"by":[126],"exploiting":[127],"within":[130],"ensemble.":[132],"We":[133],"show":[134,161],"bound":[137],"for":[138],"datasets":[147],"supports":[149],"intuition":[151],"Fed-ET.":[153],"Our":[154],"experiments":[155],"image":[157],"language":[159],"tasks":[160],"significantly":[164],"outperforms":[165],"other":[166],"state-of-the-art":[167],"fewer":[171],"communicated":[172],"parameters,":[173],"is":[175],"also":[176],"robust":[177],"against":[178],"high":[179],"data-heterogeneity.":[180]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":32},{"year":2024,"cited_by_count":42},{"year":2023,"cited_by_count":18}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}