{"id":"https://openalex.org/W4415708863","doi":"https://doi.org/10.1109/icme59968.2025.11209404","title":"Local Model Trajectory Matching for Data Heterogeneity in Federated Learning","display_name":"Local Model Trajectory Matching for Data Heterogeneity in Federated Learning","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708863","doi":"https://doi.org/10.1109/icme59968.2025.11209404"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209404","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209404","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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/A5076606414","display_name":"Mingyu Zhao","orcid":"https://orcid.org/0000-0002-6230-8399"},"institutions":[{"id":"https://openalex.org/I142108993","display_name":"Southwest University","ror":"https://ror.org/01kj4z117","country_code":"CN","type":"education","lineage":["https://openalex.org/I142108993"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Man Zhao","raw_affiliation_strings":["Southwest University,College of Computer and Information Science,Chongqing,China"],"affiliations":[{"raw_affiliation_string":"Southwest University,College of Computer and Information Science,Chongqing,China","institution_ids":["https://openalex.org/I142108993"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017901850","display_name":"Tingting Leng","orcid":null},"institutions":[{"id":"https://openalex.org/I142108993","display_name":"Southwest University","ror":"https://ror.org/01kj4z117","country_code":"CN","type":"education","lineage":["https://openalex.org/I142108993"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tingting Leng","raw_affiliation_strings":["Southwest University,College of Computer and Information Science,Chongqing,China"],"affiliations":[{"raw_affiliation_string":"Southwest University,College of Computer and Information Science,Chongqing,China","institution_ids":["https://openalex.org/I142108993"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100781212","display_name":"Jun Zhou","orcid":"https://orcid.org/0000-0001-5822-8233"},"institutions":[{"id":"https://openalex.org/I142108993","display_name":"Southwest University","ror":"https://ror.org/01kj4z117","country_code":"CN","type":"education","lineage":["https://openalex.org/I142108993"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Zhou","raw_affiliation_strings":["Southwest University,College of Computer and Information Science,Chongqing,China"],"affiliations":[{"raw_affiliation_string":"Southwest University,College of Computer and Information Science,Chongqing,China","institution_ids":["https://openalex.org/I142108993"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5076606414"],"corresponding_institution_ids":["https://openalex.org/I142108993"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17543622,"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":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.8300999999046326,"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":0.8300999999046326,"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/T11719","display_name":"Data Quality and Management","score":0.042399998754262924,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.02250000089406967,"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":0.8385000228881836},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.6183000206947327},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5835000276565552},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5766000151634216},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.5690000057220459},{"id":"https://openalex.org/keywords/forgetting","display_name":"Forgetting","score":0.4133000075817108},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.40470001101493835},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.3734000027179718}],"concepts":[{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.8385000228881836},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8187999725341797},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.6183000206947327},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5835000276565552},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5766000151634216},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5690000057220459},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.450300008058548},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44609999656677246},{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.4133000075817108},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40619999170303345},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.40470001101493835},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3734000027179718},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.350600004196167},{"id":"https://openalex.org/C2779582901","wikidata":"https://www.wikidata.org/wiki/Q21013010","display_name":"Distributed learning","level":2,"score":0.34380000829696655},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.31220000982284546},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.31029999256134033},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2806999981403351},{"id":"https://openalex.org/C70061542","wikidata":"https://www.wikidata.org/wiki/Q989016","display_name":"Distributed database","level":2,"score":0.2759000062942505},{"id":"https://openalex.org/C141934464","wikidata":"https://www.wikidata.org/wiki/Q3305386","display_name":"Local optimum","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C2778058735","wikidata":"https://www.wikidata.org/wiki/Q4692253","display_name":"Aggregate data","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209404","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209404","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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/W3096572172","https://openalex.org/W3178661111","https://openalex.org/W3182158470","https://openalex.org/W3204874618","https://openalex.org/W4226101686","https://openalex.org/W4287332481","https://openalex.org/W4382463479","https://openalex.org/W4386065957","https://openalex.org/W4386075560","https://openalex.org/W4386076561","https://openalex.org/W4386767075","https://openalex.org/W4391250546","https://openalex.org/W4393146407","https://openalex.org/W4393973089","https://openalex.org/W4396237233","https://openalex.org/W4400877862","https://openalex.org/W4401211592","https://openalex.org/W4402703097"],"related_works":[],"abstract_inverted_index":{"Federated":[0],"learning":[1,7,59],"is":[2,163],"a":[3,22,56],"new":[4],"distributed":[5],"machine":[6],"paradigm":[8],"that":[9,63,154],"enables":[10],"collaborative":[11],"training":[12],"while":[13],"preserving":[14],"user":[15],"data":[16,19,69,95],"privacy.":[17],"However,":[18],"heterogeneity":[20],"remains":[21],"critical":[23],"challenge":[24],"in":[25,82,165],"federated":[26,58],"learning.":[27],"Models":[28],"trained":[29],"on":[30,131],"imbalanced":[31],"client":[32,77,140,149],"datasets":[33],"often":[34],"converge":[35],"to":[36,44,87,99,127],"local":[37,72,84],"optima,":[38],"causing":[39],"the":[40,47,65,79,89,101,112],"aggregated":[41],"global":[42,48,66,102,113,118,135],"model":[43,67,85,119,136,144],"deviate":[45],"from":[46,121],"optimum.":[49,114],"To":[50],"address":[51],"this":[52],"challenge,":[53],"we":[54,116],"propose":[55],"novel":[57],"method":[60],"called":[61],"FedLTM":[62,157],"fine-tunes":[64],"using":[68],"synthesized":[70],"via":[71],"trajectory":[73],"matching.":[74],"Specifically,":[75],"each":[76],"utilizes":[78],"dynamic":[80],"changes":[81],"its":[83],"parameters":[86,120],"guide":[88],"generation":[90],"of":[91],"pseudo-data.":[92],"These":[93],"synthetic":[94],"are":[96],"then":[97],"used":[98],"fine-tune":[100],"model,":[103],"effectively":[104],"reducing":[105],"aggregation":[106],"bias":[107],"and":[108,146],"facilitating":[109],"convergence":[110],"toward":[111],"Furthermore,":[115],"aggregate":[117],"different":[122],"stages":[123],"as":[124],"teacher":[125,143],"models":[126],"perform":[128],"knowledge":[129],"distillation":[130],"clients.":[132],"It":[133],"mitigates":[134],"forgetting":[137],"under":[138],"low":[139],"participation,":[141],"enhances":[142],"stability,":[145],"better":[147],"corrects":[148],"drift.":[150],"Extensive":[151],"experiments":[152],"demonstrate":[153],"our":[155],"proposed":[156],"outperforms":[158],"state-of-the-art":[159],"baselines.":[160],"Our":[161],"code":[162],"available":[164],"https://github.com/Man-zhao/FedLTM.":[166]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-30T00:00:00"}