{"id":"https://openalex.org/W7167642451","doi":"https://doi.org/10.48550/arxiv.2607.03763","title":"FedACT: Federated Adaptive Coordinate Trust Modulation for Robust Transformer Training under Data Heterogeneity","display_name":"FedACT: Federated Adaptive Coordinate Trust Modulation for Robust Transformer Training under Data Heterogeneity","publication_year":2026,"publication_date":"2026-07-04","ids":{"openalex":"https://openalex.org/W7167642451","doi":"https://doi.org/10.48550/arxiv.2607.03763"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2607.03763","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.03763","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.2607.03763","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5140213471","display_name":"Shuai Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Shuai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140214104","display_name":"Qinglin Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Qinglin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140214426","display_name":"Ping Luo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, Ping","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140175969","display_name":"Jiahuan Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Jiahuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112323233","display_name":"Haiyao Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Hongyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140204230","display_name":"Haotian Mo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mo, Haotian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080941103","display_name":"Yigui Feng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng, Yigui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140218411","display_name":"Ziang Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Ziang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001387315","display_name":"Qisong Xiao","orcid":"https://orcid.org/0009-0007-5780-2118"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiao, Qisong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140204422","display_name":"Jie Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Jie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5140199762","display_name":"Tao Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Tao","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":0.1371999979019165,"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":0.1371999979019165,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.13670000433921814,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.12099999934434891,"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/federated-learning","display_name":"Federated learning","score":0.6022999882698059},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.47679999470710754},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.41350001096725464},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.36719998717308044},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.362199991941452}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7698000073432922},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.6022999882698059},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.47679999470710754},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.41350001096725464},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4068000018596649},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.36719998717308044},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.362199991941452},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2921999990940094},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25130000710487366},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.24330000579357147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2607.03763","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.03763","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.2607.03763","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.03763","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Federated":[0],"Transformer":[1,155],"training":[2],"increasingly":[3],"relies":[4],"on":[5,124,130,154],"local":[6,15,114],"AdamW,":[7],"whose":[8],"adaptive":[9,48,64,93,148],"updates":[10,29,123],"can":[11],"provide":[12],"much":[13],"stronger":[14,158],"progress":[16],"than":[17],"SGD-based":[18],"training.":[19,86],"However,":[20],"under":[21,157],"heterogeneous":[22],"client":[23],"data,":[24],"even":[25],"globally":[26,91],"corrected":[27,63,92],"AdamW":[28,85],"may":[30],"remain":[31],"highly":[32],"uneven":[33],"in":[34],"coordinate-wise":[35,103],"reliability.":[36],"We":[37],"refer":[38],"to":[39,101,109],"this":[40,72],"phenomenon":[41],"as":[42],"coordinate":[43,79],"trust":[44,80,104,174],"mismatch.":[45],"Existing":[46],"federated":[47,84,131,147],"optimizers":[49],"mainly":[50],"address":[51],"mismatch":[52],"at":[53],"the":[54,62,125,151],"client-update":[55],"or":[56],"communication-round":[57],"level,":[58],"but":[59],"still":[60],"apply":[61],"direction":[65,94,169],"densely":[66],"and":[67,95,116,137],"uniformly":[68],"across":[69],"coordinates.":[70,127],"In":[71],"paper,":[73],"we":[74],"propose":[75],"FedACT,":[76],"a":[77,90,102],"global-aware":[78],"modulation":[81],"method":[82],"for":[83],"FedACT":[87,142,166],"first":[88],"forms":[89],"then":[96],"reallocates":[97],"update":[98],"magnitudes":[99],"according":[100],"score,":[105],"assigning":[106],"larger":[107],"steps":[108],"coordinates":[110],"jointly":[111],"supported":[112],"by":[113],"gradients":[115],"global":[117],"correction,":[118],"while":[119],"preserving":[120],"smaller":[121],"non-zero":[122],"remaining":[126],"Extensive":[128],"experiments":[129],"vision":[132],"Transformers,":[133],"CNNs,":[134],"LLM":[135,138],"pre-training,":[136],"fine-tuning":[139],"show":[140,164],"that":[141,165,172],"consistently":[143],"improves":[144,167],"over":[145],"strong":[146],"baselines,":[149],"with":[150],"largest":[152],"gains":[153],"models":[156],"data":[159],"heterogeneity.":[160],"Mechanism":[161],"analyses":[162],"further":[163],"cross-client":[168],"consistency,":[170],"suggesting":[171],"coordinate-level":[173],"allocation":[175],"effectively":[176],"complements":[177],"round-level":[178],"global-local":[179],"correction.":[180],"Code":[181],"will":[182],"be":[183],"released.":[184]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-07-08T00:00:00"}