{"id":"https://openalex.org/W7125803876","doi":"https://doi.org/10.1109/ijcnn64981.2025.11361390","title":"Federated Meta Learning for Cross-Domain Personalization with Partial Model Initialization","display_name":"Federated Meta Learning for Cross-Domain Personalization with Partial Model Initialization","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W7125803876","doi":"https://doi.org/10.1109/ijcnn64981.2025.11361390"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11361390","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11361390","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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/A5123955788","display_name":"Ayshika Kapoor","orcid":null},"institutions":[{"id":"https://openalex.org/I154851008","display_name":"Indian Institute of Technology Roorkee","ror":"https://ror.org/00582g326","country_code":"IN","type":"education","lineage":["https://openalex.org/I154851008"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Ayshika Kapoor","raw_affiliation_strings":["Indian Institute of Technology Roorkee,Department of Electronics and Communication Engineering,Uttarakhand,India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Roorkee,Department of Electronics and Communication Engineering,Uttarakhand,India","institution_ids":["https://openalex.org/I154851008"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123887091","display_name":"Dheeraj Kumar","orcid":null},"institutions":[{"id":"https://openalex.org/I154851008","display_name":"Indian Institute of Technology Roorkee","ror":"https://ror.org/00582g326","country_code":"IN","type":"education","lineage":["https://openalex.org/I154851008"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Dheeraj Kumar","raw_affiliation_strings":["Indian Institute of Technology Roorkee,Department of Electronics and Communication Engineering,Uttarakhand,India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Roorkee,Department of Electronics and Communication Engineering,Uttarakhand,India","institution_ids":["https://openalex.org/I154851008"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5123955788"],"corresponding_institution_ids":["https://openalex.org/I154851008"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87622743,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.921500027179718,"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":0.921500027179718,"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":0.01640000008046627,"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/T14347","display_name":"Big Data and Digital Economy","score":0.004800000227987766,"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/initialization","display_name":"Initialization","score":0.757099986076355},{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.7394999861717224},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.5845000147819519},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5723000168800354},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5625},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5530999898910522},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.5146999955177307}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8026000261306763},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.757099986076355},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.7394999861717224},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.5845000147819519},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5723000168800354},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5625},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5530999898910522},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.5146999955177307},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42329999804496765},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41280001401901245},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.3955000042915344},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3849000036716461},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.31529998779296875},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.30550000071525574},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.29980000853538513},{"id":"https://openalex.org/C2781002164","wikidata":"https://www.wikidata.org/wiki/Q6822311","display_name":"Meta learning (computer science)","level":3,"score":0.2921000123023987},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2793999910354614},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.27149999141693115},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.2696000039577484}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11361390","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11361390","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1722318740","https://openalex.org/W2053637704","https://openalex.org/W2627183927","https://openalex.org/W2763549966","https://openalex.org/W2981720610","https://openalex.org/W2995022099","https://openalex.org/W3133814152","https://openalex.org/W3169044395","https://openalex.org/W3200223987","https://openalex.org/W4283792986","https://openalex.org/W4292737460","https://openalex.org/W4295308640","https://openalex.org/W4312797616","https://openalex.org/W4388469770","https://openalex.org/W4390871797","https://openalex.org/W4401072857","https://openalex.org/W4402352386","https://openalex.org/W4402352871"],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,13,42,57,66,84,132,159],"rapid":[2],"deployment":[3],"of":[4,16,45,59,126,161,177],"edge":[5,31],"devices,":[6],"there":[7],"has":[8,23],"been":[9],"growing":[10],"concern":[11],"over":[12],"privacy":[14],"preservation":[15],"clients\u2019":[17,102,120],"private":[18],"data.":[19],"Federated":[20],"learning":[21],"(FL)":[22],"emerged":[24],"as":[25,41,156,235],"a":[26,124,148,162,174,186,249],"promising":[27],"solution":[28,253],"that":[29,56,189,242],"enables":[30],"devices":[32],"for":[33,254],"collaborative":[34],"model":[35,86,115,122,127,134,164,194,207],"training":[36],"without":[37],"compromising":[38],"data":[39,67,89,145,167,178],"privacy,":[40],"local":[43,88,121,137,214],"datasets":[44,103],"clients":[46,70,220],"are":[47,71,129],"not":[48],"shared":[49,210],"directly.":[50],"However,":[51,139],"previous":[52],"works":[53],"have":[54,104],"shown":[55],"performance":[58],"conventional":[60],"FL":[61,78,94,256],"approaches":[62],"significantly":[63],"deteriorates":[64],"when":[65,101],"distributions":[68,146,168],"across":[69,143,165,219],"heterogeneous":[72],"or":[73],"non-IID.":[74],"Integrating":[75],"personalization":[76,199],"into":[77,209],"addresses":[79],"these":[80],"challenges":[81],"by":[82,171],"adapting":[83],"global":[85,133,163,211],"to":[87,99,109,118,196,224],"distributions,":[90],"but":[91],"existing":[92],"personalized":[93],"(PFL)":[95],"frameworks":[96],"often":[97],"fail":[98],"generalize":[100],"cross-domain":[105,198,231,255],"features.":[106],"One":[107],"approach":[108,205],"mitigate":[110],"this":[111,181],"challenge":[112],"is":[113,154],"partial":[114,193],"initialization,":[116],"where":[117],"update":[119],"only":[123,173],"subset":[125],"parameters":[128,208],"initialized":[130],"from":[131],"while":[135,221],"retaining":[136],"parameters.":[138],"obtaining":[140],"effective":[141,217],"generalization":[142,218],"distinct":[144,166],"remains":[147],"challenge.":[149],"In":[150,180],"such":[151,234],"instances,":[152],"meta-learning":[153,191],"preferred":[155],"it":[157,248],"provides":[158],"adaptation":[160],"and":[169,200,212,239,251],"tasks":[170],"employing":[172],"small":[175],"number":[176],"samples.":[179],"paper,":[182],"we":[183],"propose":[184],"MetaPartialFL,":[185],"novel":[187],"framework":[188],"integrates":[190],"with":[192],"initialization":[195],"address":[197],"heterogeneity":[201],"in":[202],"FL.":[203],"The":[204],"partitions":[206],"client-specific":[213],"components,":[215],"enabling":[216],"maintaining":[222],"adaptability":[223],"each":[225],"client\u2019s":[226],"datasets.":[227],"Extensive":[228],"evaluations":[229],"on":[230],"benchmark":[232],"datasets,":[233],"Office-Home,":[236],"Office-31,":[237],"PACS,":[238],"DomainNet,":[240],"demonstrate":[241],"MetaPartialFL":[243],"outperforms":[244],"state-of-the-art":[245],"methods,":[246],"making":[247],"robust":[250],"efficient":[252],"applications.":[257]},"counts_by_year":[],"updated_date":"2026-02-23T20:09:44.859080","created_date":"2026-01-28T00:00:00"}