{"id":"https://openalex.org/W4402351413","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650808","title":"Fractal Augmented Pre-training and Gaussian Virtual Feature Calibration for Tackling Data Heterogeneity in Federated Learning","display_name":"Fractal Augmented Pre-training and Gaussian Virtual Feature Calibration for Tackling Data Heterogeneity in Federated Learning","publication_year":2024,"publication_date":"2024-06-30","ids":{"openalex":"https://openalex.org/W4402351413","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650808"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn60899.2024.10650808","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn60899.2024.10650808","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 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/A5107862406","display_name":"Yan Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yan Zheng","raw_affiliation_strings":["Beijing Institute of Technology,School of Cyberspace Science and Technology,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,School of Cyberspace Science and Technology,Beijing,China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011730425","display_name":"Yanlong Zhai","orcid":"https://orcid.org/0000-0002-0168-8308"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanlong Zhai","raw_affiliation_strings":["Beijing Institute of Technology,School of Cyberspace Science and Technology,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,School of Cyberspace Science and Technology,Beijing,China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111276827","display_name":"Yanglin Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanglin Liu","raw_affiliation_strings":["Beijing Institute of Technology,School of Cyberspace Science and Technology,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,School of Cyberspace Science and Technology,Beijing,China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101882153","display_name":"You Li","orcid":"https://orcid.org/0000-0002-2246-9366"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"You Li","raw_affiliation_strings":["Beijing Institute of Technology,School of Cyberspace Science and Technology,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,School of Cyberspace Science and Technology,Beijing,China","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5107862406"],"corresponding_institution_ids":["https://openalex.org/I125839683"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12869883,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"34","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":0.9998000264167786,"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":0.9998000264167786,"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":0.9807000160217285,"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/T11448","display_name":"Face recognition and analysis","score":0.978600025177002,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/feature","display_name":"Feature (linguistics)","score":0.691829264163971},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6852811574935913},{"id":"https://openalex.org/keywords/fractal","display_name":"Fractal","score":0.6726663112640381},{"id":"https://openalex.org/keywords/calibration","display_name":"Calibration","score":0.6081043481826782},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5808007121086121},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5619126558303833},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.5306412577629089},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.529676079750061},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4486716091632843},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37299397587776184},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16387373208999634},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1311292052268982},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.09357377886772156}],"concepts":[{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.691829264163971},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6852811574935913},{"id":"https://openalex.org/C40636538","wikidata":"https://www.wikidata.org/wiki/Q81392","display_name":"Fractal","level":2,"score":0.6726663112640381},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.6081043481826782},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5808007121086121},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5619126558303833},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5306412577629089},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.529676079750061},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4486716091632843},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37299397587776184},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16387373208999634},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1311292052268982},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.09357377886772156},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn60899.2024.10650808","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn60899.2024.10650808","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2913668833","https://openalex.org/W2942810103","https://openalex.org/W2963819344","https://openalex.org/W3042621011","https://openalex.org/W3048392890","https://openalex.org/W3080934299","https://openalex.org/W3159576603","https://openalex.org/W3168213397","https://openalex.org/W3176639943","https://openalex.org/W3182158470","https://openalex.org/W3189545149","https://openalex.org/W3213291156","https://openalex.org/W4285603347","https://openalex.org/W4292829107","https://openalex.org/W4361756856","https://openalex.org/W4365802619","https://openalex.org/W4382239439","https://openalex.org/W6728757088","https://openalex.org/W6761472960","https://openalex.org/W6763048141","https://openalex.org/W6764733053","https://openalex.org/W6767737316","https://openalex.org/W6795843344","https://openalex.org/W6810638590","https://openalex.org/W6838907135","https://openalex.org/W6843195772","https://openalex.org/W6845589855","https://openalex.org/W6845997457","https://openalex.org/W6853177463"],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2013332237","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W3216976533","https://openalex.org/W1522259561","https://openalex.org/W4394050964","https://openalex.org/W2551249631"],"abstract_inverted_index":{"Federated":[0,134],"learning":[1,247],"(FL)":[2],"enables":[3],"collaborative":[4],"model":[5,85,106,124,219,223],"training":[6,63],"across":[7],"multiple":[8],"clients":[9],"while":[10,232],"preserving":[11],"privacy.":[12,89],"In":[13,126],"practical":[14],"situations,":[15],"the":[16,22,29,32,62,78,83,104,118,166,174,191,196],"heterogeneous":[17],"and":[18,55,94,101,110,152,178,206,230,236,249],"unbalanced":[19],"distribution":[20,121],"of":[21,31,70,77,103],"data":[23,80,109,120,168,180,212,228],"has":[24,37],"a":[25,68],"significant":[26],"impact":[27],"on":[28,117,187],"performance":[30,224],"model.":[33],"Although":[34],"some":[35],"work":[36],"been":[38],"carried":[39],"out":[40],"to":[41,60,73,81,137,193,210],"address":[42],"this":[43,127,139],"issue,":[44],"such":[45],"as":[46],"adding":[47],"regularization":[48],"terms,":[49],"employing":[50],"specific":[51],"server":[52,192],"aggregation":[53],"strategies,":[54],"utilizing":[56],"deep":[57],"generative":[58],"models":[59],"augment":[61],"data,":[64],"there":[65],"is":[66],"still":[67],"lack":[69],"efficient":[71],"approaches":[72],"derive":[74],"intrinsic":[75],"representation":[76],"local":[79],"improve":[82,123],"global":[84,105],"without":[86],"compromising":[87],"client":[88,119,179,189],"Through":[90],"our":[91,215],"careful":[92],"observations":[93],"analysis,":[95],"we":[96,129,172],"found":[97],"that":[98,113,242],"incorporating":[99],"pre-training":[100,145],"calibrating":[102],"using":[107,185],"virtual":[108,111,150,157,167,177,201],"features":[112],"are":[114],"generated":[115,169],"based":[116],"can":[122,250],"generalization.":[125],"work,":[128],"propose":[130],"Virtual":[131],"Data":[132],"Augmented":[133,147],"Learning":[135],"(FedVDA)":[136],"resolve":[138],"problem.":[140],"Specifically,":[141],"FedVDA":[142,243],"combines":[143],"unsupervised":[144],"with":[146,198,227,253],"Fractal":[148],"(AF)":[149],"images":[151],"Gaussian":[153],"Mixture":[154],"Model":[155],"(GMM)":[156],"feature":[158,183],"calibration.":[159],"By":[160],"integrating":[161],"color":[162],"tone":[163],"transformations":[164],"into":[165],"by":[170],"fractals,":[171],"bridge":[173],"gap":[175],"between":[176],"distributions.":[181],"Multi-modal":[182],"modeling":[184],"variances":[186],"each":[188],"allows":[190],"efficiently":[194],"calibrate":[195],"classifier":[197],"balanced":[199],"sampled":[200],"features,":[202,220],"reducing":[203],"both":[204],"computational":[205,235],"communication":[207,237],"overhead.":[208],"Compared":[209],"other":[211,254],"augmentation":[213],"methods,":[214],"method":[216],"directly":[217],"calibrates":[218],"significantly":[221],"improving":[222],"in":[225],"scenarios":[226],"heterogeneity":[229],"imbalance,":[231],"minimizing":[233],"additional":[234],"costs.":[238],"Our":[239],"experiments":[240],"demonstrate":[241],"outperforms":[244],"existing":[245],"federated":[246],"methods":[248],"seamlessly":[251],"integrate":[252],"algorithms.":[255]},"counts_by_year":[],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}