{"id":"https://openalex.org/W7124164775","doi":"https://doi.org/10.1109/icpads67057.2025.11322895","title":"FedSAGA: Composite Federated Learning with Inertial Douglas-Rachford Splitting and Variance Reduction Method","display_name":"FedSAGA: Composite Federated Learning with Inertial Douglas-Rachford Splitting and Variance Reduction Method","publication_year":2025,"publication_date":"2025-12-14","ids":{"openalex":"https://openalex.org/W7124164775","doi":"https://doi.org/10.1109/icpads67057.2025.11322895"},"language":null,"primary_location":{"id":"doi:10.1109/icpads67057.2025.11322895","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpads67057.2025.11322895","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5023264498","display_name":"Jiao Xue","orcid":"https://orcid.org/0009-0003-4385-142X"},"institutions":[{"id":"https://openalex.org/I136765683","display_name":"Tianjin University of Technology","ror":"https://ror.org/00zbe0w13","country_code":"CN","type":"education","lineage":["https://openalex.org/I136765683"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiao Xue","raw_affiliation_strings":["School of Computer Science and Engineering, Tianjin University of Technology,Tianjin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Tianjin University of Technology,Tianjin,China","institution_ids":["https://openalex.org/I136765683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5122983969","display_name":"Chundong Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107650","display_name":"Tianjin Vocational Institute","ror":"https://ror.org/012tjde79","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210107650"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chundong Wang","raw_affiliation_strings":["School of Computer Science and Engineering, Tianjin University of Technology, Tianjin Public Security Police Vocational College,Tianjin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Tianjin University of Technology, Tianjin Public Security Police Vocational College,Tianjin,China","institution_ids":["https://openalex.org/I4210107650"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.673,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.89001232,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.8108000159263611,"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":0.8108000159263611,"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":0.1581999957561493,"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/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.003599999938160181,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6462000012397766},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.6096000075340271},{"id":"https://openalex.org/keywords/rate-of-convergence","display_name":"Rate of convergence","score":0.6062999963760376},{"id":"https://openalex.org/keywords/variance-reduction","display_name":"Variance reduction","score":0.5845999717712402},{"id":"https://openalex.org/keywords/extrapolation","display_name":"Extrapolation","score":0.5605999827384949},{"id":"https://openalex.org/keywords/sublinear-function","display_name":"Sublinear function","score":0.5351999998092651},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4700999855995178},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.412200003862381}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6635000109672546},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6462000012397766},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.6096000075340271},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.6062999963760376},{"id":"https://openalex.org/C62644790","wikidata":"https://www.wikidata.org/wiki/Q3454689","display_name":"Variance reduction","level":3,"score":0.5845999717712402},{"id":"https://openalex.org/C132459708","wikidata":"https://www.wikidata.org/wiki/Q744069","display_name":"Extrapolation","level":2,"score":0.5605999827384949},{"id":"https://openalex.org/C117160843","wikidata":"https://www.wikidata.org/wiki/Q338652","display_name":"Sublinear function","level":2,"score":0.5351999998092651},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5170999765396118},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4700999855995178},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.412200003862381},{"id":"https://openalex.org/C121683094","wikidata":"https://www.wikidata.org/wiki/Q3554721","display_name":"Control variates","level":5,"score":0.40549999475479126},{"id":"https://openalex.org/C157972887","wikidata":"https://www.wikidata.org/wiki/Q463359","display_name":"Convex optimization","level":3,"score":0.39070001244544983},{"id":"https://openalex.org/C11210021","wikidata":"https://www.wikidata.org/wiki/Q1520713","display_name":"Linearization","level":3,"score":0.3734999895095825},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36390000581741333},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.3483000099658966},{"id":"https://openalex.org/C112680207","wikidata":"https://www.wikidata.org/wiki/Q714886","display_name":"Regular polygon","level":2,"score":0.3458999991416931},{"id":"https://openalex.org/C173386949","wikidata":"https://www.wikidata.org/wiki/Q192735","display_name":"Inertial frame of reference","level":2,"score":0.34139999747276306},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.3091000020503998},{"id":"https://openalex.org/C145446738","wikidata":"https://www.wikidata.org/wiki/Q319913","display_name":"Convex function","level":3,"score":0.2903999984264374},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2750000059604645},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpads67057.2025.11322895","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpads67057.2025.11322895","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS)","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":21,"referenced_works":["https://openalex.org/W1988720110","https://openalex.org/W2047152541","https://openalex.org/W2048408528","https://openalex.org/W2808402975","https://openalex.org/W2942896838","https://openalex.org/W2963433607","https://openalex.org/W3012957388","https://openalex.org/W3048036474","https://openalex.org/W4224919778","https://openalex.org/W4229650096","https://openalex.org/W4244393449","https://openalex.org/W4292615914","https://openalex.org/W4308826495","https://openalex.org/W4315488555","https://openalex.org/W4385371323","https://openalex.org/W4393147298","https://openalex.org/W4393207744","https://openalex.org/W4404848415","https://openalex.org/W4405968064","https://openalex.org/W4406142677","https://openalex.org/W4406215352"],"related_works":[],"abstract_inverted_index":{"Composite":[0],"federated":[1,75],"learning":[2,10],"provides":[3],"a":[4,66,80,89,108,147,156],"comprehensive":[5],"framework":[6,22],"for":[7],"addressing":[8],"machine":[9],"tasks":[11],"that":[12,78,144],"incorporate":[13],"regularization":[14,83],"terms.":[15],"Nevertheless,":[16],"numerous":[17],"established":[18],"methods":[19],"within":[20],"this":[21],"face":[23],"challenges":[24],"stemming":[25],"from":[26],"data":[27],"heterogeneity":[28],"and":[29,50,57,94,124,155,170],"the":[30,54,92,112,117,133,139,175,178],"high":[31],"variance":[32,118],"induced":[33],"by":[34,120],"stochastic":[35,121],"gradients":[36],"mapping.":[37],"These":[38],"issues":[39],"cause":[40],"significant":[41],"deviations":[42],"in":[43,48],"clients'":[44],"local":[45,96],"models,":[46],"resulting":[47],"unstable":[49],"slow":[51],"convergence":[52,149,158,176],"of":[53,91,177],"global":[55,82],"model":[56,97],"increased":[58],"communication":[59,102],"costs.":[60],"To":[61,127],"address":[62],"this,":[63],"we":[64,87,131],"propose":[65],"novel":[67],"algorithm":[68,180],"named":[69],"FedSAGA,":[70,86],"designed":[71],"to":[72,115],"solve":[73],"composite":[74],"optimization":[76],"problems":[77],"include":[79],"nonsmooth":[81],"term.":[84],"In":[85],"construct":[88],"combination":[90],"latest":[93],"historical":[95],"updates":[98],"without":[99],"incurring":[100],"additional":[101],"overhead.":[103],"This":[104],"estimate":[105],"serves":[106],"as":[107],"control":[109],"variate":[110],"on":[111,167],"client":[113,125,183],"side":[114],"reduce":[116],"introduced":[119],"gradient":[122],"mapping":[123],"sampling.":[126],"further":[128],"accelerate":[129],"convergence,":[130],"leverage":[132],"inertial":[134],"extrapolation":[135],"step":[136],"locally":[137],"at":[138],"clients.":[140],"Theoretical":[141],"analysis":[142],"demonstrates":[143],"FedSAGA":[145],"attains":[146],"sublinear":[148],"rate":[150,159],"under":[151,160,181],"general":[152],"convex":[153,162],"settings":[154],"linear":[157],"strongly":[161],"settings.":[163],"Numerical":[164],"experiments":[165],"based":[166],"both":[168],"real":[169],"synthetic":[171],"datasets":[172],"effectively":[173],"demonstrate":[174],"proposed":[179],"partial":[182],"participation.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-01-15T00:00:00"}