{"id":"https://openalex.org/W7168351266","doi":"https://doi.org/10.48550/arxiv.2607.12583","title":"Scaling Synthetic-Image Pre-Training for Federated Fine-Tuning of Large Vision Models","display_name":"Scaling Synthetic-Image Pre-Training for Federated Fine-Tuning of Large Vision Models","publication_year":2026,"publication_date":"2026-07-14","ids":{"openalex":"https://openalex.org/W7168351266","doi":"https://doi.org/10.48550/arxiv.2607.12583"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2607.12583","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.12583","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2607.12583","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5140808293","display_name":"Qianpiao Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Qianpiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140959850","display_name":"Xiaozhu Song","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song, Xiaozhu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140860807","display_name":"Junlong Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Junlong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140757702","display_name":"Yue Zeng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zeng, Yue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140885012","display_name":"Jianchun Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Jianchun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5140799815","display_name":"Huaqing Tu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tu, Huaqing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.1412999927997589,"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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.1412999927997589,"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"}},{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.09769999980926514,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.05400000140070915,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/testbed","display_name":"Testbed","score":0.6434999704360962},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5791000127792358},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.47699999809265137},{"id":"https://openalex.org/keywords/resource-allocation","display_name":"Resource allocation","score":0.47290000319480896},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4530999958515167},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4487999975681305},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4025999903678894},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.39410001039505005}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7937999963760376},{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.6434999704360962},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5791000127792358},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.47699999809265137},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.47290000319480896},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4530999958515167},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4487999975681305},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40549999475479126},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4025999903678894},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.39410001039505005},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3725999891757965},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.36230000853538513},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.362199991941452},{"id":"https://openalex.org/C81293917","wikidata":"https://www.wikidata.org/wiki/Q4189534","display_name":"System deployment","level":3,"score":0.34599998593330383},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.33629998564720154},{"id":"https://openalex.org/C2777958785","wikidata":"https://www.wikidata.org/wiki/Q17120940","display_name":"Resource efficiency","level":2,"score":0.321399986743927},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3000999987125397},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.29809999465942383},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2696000039577484},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.26579999923706055},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2531000077724457}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2607.12583","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.12583","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2607.12583","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.12583","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"score":0.5688546895980835,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Federated":[0],"fine-tuning":[1,57],"(FedFT)":[2],"enables":[3],"adapting":[4],"pre-trained":[5],"large":[6],"vision":[7],"models":[8,42],"(LVMs)":[9],"on":[10,43,212],"distributed,":[11],"privacy-sensitive":[12],"devices,":[13],"while":[14,85,206,231],"its":[15],"practical":[16],"deployment":[17],"is":[18],"hindered":[19],"by":[20,39,222,228],"three":[21],"critical":[22,97],"challenges:":[23],"resource":[24,66],"constraints,":[25],"system":[26,208],"heterogeneity,":[27],"and":[28,71,106,137,186,192,225],"non-IID":[29,52,184],"data.":[30],"While":[31],"prior":[32],"studies":[33],"partially":[34],"address":[35],"these":[36,122],"issues,":[37],"e.g.,":[38],"pre-training":[40,105,136,155,165,181],"initial":[41],"synthetic":[44,75,162,172],"images":[45],"to":[46,64,80,116,139,156,182,198,235],"mitigate":[47],"the":[48,101,133,141,158,213],"adverse":[49],"effects":[50],"of":[51,104,161],"data,":[53,185],"or":[54],"leveraging":[55],"parameter-efficient":[56],"(PEFT)":[58],"methods":[59,78,89],"like":[60],"low-rank":[61],"adaptation":[62],"(LoRA)":[63],"reduce":[65],"consumption,":[67],"they":[68],"remain":[69],"inadequate":[70],"fragmented.":[72],"Specifically,":[73,146],"existing":[74],"image":[76,173],"generation":[77,174],"fail":[79],"capture":[81],"device-specific":[82,177],"feature":[83,178],"distributions,":[84],"current":[86],"PEFT-based":[87],"FedFT":[88,107,138,154,197],"often":[90],"undervalue":[91],"weaker":[92],"devices":[93,202],"that":[94,130,175,200,217],"may":[95],"provide":[96],"information.":[98],"More":[99],"importantly,":[100],"separate":[102],"optimization":[103],"neglects":[108],"their":[109],"inherent":[110],"connection,":[111],"lacking":[112],"a":[113,127,150,188],"holistic":[114],"perspective":[115],"maximize":[117],"training":[118,144],"efficiency.":[119],"To":[120],"overcome":[121],"limitations,":[123],"we":[124],"propose":[125],"FeDiSyn,":[126],"unified":[128],"framework":[129],"holistically":[131],"considers":[132],"interplay":[134],"between":[135],"minimize":[140],"overall":[142],"LVM":[143],"time.":[145],"FeDiSyn":[147,218],"introduces:":[148],"(i)":[149],"scaling":[151],"law":[152],"for":[153,180,196],"determine":[157],"optimal":[159],"number":[160],"images,":[163],"balancing":[164],"benefit":[166],"against":[167],"generation/pre-training":[168],"cost,":[169],"(ii)":[170],"diffusion-based":[171],"captures":[176],"distributions":[179],"tackle":[183],"(iii)":[187],"contribution-aware":[189],"LoRA":[190],"configuration":[191],"bandwidth":[193],"allocation":[194],"algorithm":[195],"ensure":[199],"informative":[201],"are":[203],"effectively":[204],"utilized":[205],"addressing":[207],"heterogeneity.":[209],"Experimental":[210],"results":[211],"real-world":[214],"testbed":[215],"demonstrate":[216],"reduces":[219],"completion":[220],"time":[221],"over":[223,229],"52.5%":[224],"communication":[226],"cost":[227],"97.2%,":[230],"achieving":[232],"comparable":[233],"accuracy":[234],"state-of-the-art":[236],"solutions.":[237]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-07-16T00:00:00"}