{"id":"https://openalex.org/W4414199257","doi":"https://doi.org/10.1109/tpami.2025.3610169","title":"Adaptive Batch Size Time Evolving Stochastic Gradient Descent for Federated Learning","display_name":"Adaptive Batch Size Time Evolving Stochastic Gradient Descent for Federated Learning","publication_year":2025,"publication_date":"2025-09-15","ids":{"openalex":"https://openalex.org/W4414199257","doi":"https://doi.org/10.1109/tpami.2025.3610169","pmid":"https://pubmed.ncbi.nlm.nih.gov/40953432"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2025.3610169","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3610169","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5086964127","display_name":"Xuming An","orcid":"https://orcid.org/0000-0003-1032-5346"},"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":"Xuming An","raw_affiliation_strings":["School of Information and Electronics, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1032-5346","affiliations":[{"raw_affiliation_string":"School of Information and Electronics, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042802004","display_name":"Li Shen","orcid":"https://orcid.org/0000-0001-5659-3464"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Shen","raw_affiliation_strings":["School of Cyber Science and Technology, Shenzhen Campus of Sun Yat-sen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-5659-3464","affiliations":[{"raw_affiliation_string":"School of Cyber Science and Technology, Shenzhen Campus of Sun Yat-sen University, Shenzhen, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100866384","display_name":"Yong Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Luo","raw_affiliation_strings":["School of Computer Science, Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-2296-6370","affiliations":[{"raw_affiliation_string":"School of Computer Science, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020194895","display_name":"Han Hu","orcid":"https://orcid.org/0000-0001-7532-0496"},"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":"Han Hu","raw_affiliation_strings":["School of Information and Electronics, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7532-0496","affiliations":[{"raw_affiliation_string":"School of Information and Electronics, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":null,"display_name":"Dacheng Tao","orcid":"https://orcid.org/0000-0001-7225-5449"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dacheng Tao","raw_affiliation_strings":["JD Explore Academy, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7225-5449","affiliations":[{"raw_affiliation_string":"JD Explore Academy, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.396,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.85915069,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"48","issue":"2","first_page":"1158","last_page":"1170"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9987000226974487,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9987000226974487,"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":0.9980000257492065,"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/T10237","display_name":"Cryptography and Data Security","score":0.9930999875068665,"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/snapshot","display_name":"Snapshot (computer storage)","score":0.820900022983551},{"id":"https://openalex.org/keywords/variance-reduction","display_name":"Variance reduction","score":0.67330002784729},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6410999894142151},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.6342999935150146},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.5845000147819519},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5476999878883362},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.4823000133037567},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.43540000915527344}],"concepts":[{"id":"https://openalex.org/C55282118","wikidata":"https://www.wikidata.org/wiki/Q252683","display_name":"Snapshot (computer storage)","level":2,"score":0.820900022983551},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7233999967575073},{"id":"https://openalex.org/C62644790","wikidata":"https://www.wikidata.org/wiki/Q3454689","display_name":"Variance reduction","level":3,"score":0.67330002784729},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6410999894142151},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.6342999935150146},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.5845000147819519},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5476999878883362},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5306000113487244},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.4823000133037567},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.43540000915527344},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3758000135421753},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.34279999136924744},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.33160001039505005},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.30720001459121704},{"id":"https://openalex.org/C177918212","wikidata":"https://www.wikidata.org/wiki/Q803623","display_name":"Perturbation (astronomy)","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.29339998960494995},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.289900004863739},{"id":"https://openalex.org/C115680565","wikidata":"https://www.wikidata.org/wiki/Q5977448","display_name":"Gradient method","level":2,"score":0.2759999930858612},{"id":"https://openalex.org/C88871306","wikidata":"https://www.wikidata.org/wiki/Q7208287","display_name":"Point process","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.26489999890327454},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C148764684","wikidata":"https://www.wikidata.org/wiki/Q621751","display_name":"Approximation algorithm","level":2,"score":0.2621999979019165},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25699999928474426},{"id":"https://openalex.org/C2779466056","wikidata":"https://www.wikidata.org/wiki/Q107630651","display_name":"Time point","level":2,"score":0.2547999918460846}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2025.3610169","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3610169","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:40953432","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40953432","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1751687266","https://openalex.org/W2194775991","https://openalex.org/W2937268935","https://openalex.org/W2942057781","https://openalex.org/W3035335410","https://openalex.org/W3093828967","https://openalex.org/W3158567365","https://openalex.org/W3159481909","https://openalex.org/W3190278004","https://openalex.org/W3198924441","https://openalex.org/W3204468048","https://openalex.org/W3204946808","https://openalex.org/W4238100585"],"related_works":[],"abstract_inverted_index":{"Variance":[0],"reduction":[1,73,91,171,182],"has":[2],"been":[3],"shown":[4],"to":[5,23,75,102,163],"improve":[6],"the":[7,41,45,49,98,115,121,145,150,154,158,165,169,174,185,226],"performance":[8],"of":[9,80,168,201,202],"Stochastic":[10],"Gradient":[11],"Descent":[12],"(SGD)":[13],"in":[14,137,173],"centralized":[15],"machine":[16],"learning.":[17],"However,":[18],"when":[19],"it":[20],"is":[21,161],"extended":[22],"federated":[24,66],"learning":[25],"systems,":[26],"many":[27],"issues":[28],"may":[29],"arise,":[30],"including":[31],"(i)":[32],"mega-batch":[33,106,138],"size":[34,69,84,107,139],"settings;":[35],"(ii)":[36],"additional":[37],"noise":[38],"introduced":[39,140],"by":[40,141,184],"gradient":[42,54,92,100,142,151,175],"difference":[43,152],"between":[44,153],"current":[46,155],"iteration":[47,156],"and":[48,52,87,119,130,157,228],"snapshot":[50,159,187],"point;":[51],"(iii)":[53],"(statistical)":[55],"heterogeneity.":[56],"In":[57,94],"this":[58],"paper,":[59],"we":[60,96],"propose":[61],"a":[62,88,198],"lightweight":[63],"algorithm":[64,195],"termed":[65],"adaptive":[67,82],"batch":[68,83],"time":[70],"evolving":[71],"variance":[72,90,170,181],"(FedATEVR)":[74],"tackle":[76],"these":[77],"issues,":[78],"consisting":[79],"an":[81,104],"setting":[85],"scheme":[86],"time-evolving":[89,166],"estimator.":[93,176],"particular,":[95],"use":[97],"historical":[99,125],"information":[101,126],"set":[103],"appropriate":[105],"for":[108,205],"each":[109,148],"client,":[110,149],"which":[111,133],"can":[112,178,196,220],"steadily":[113],"accelerate":[114],"local":[116,131],"SGD":[117],"process":[118],"reduce":[120],"computation":[122],"cost.":[123],"The":[124],"involves":[127],"both":[128],"global":[129],"gradient,":[132],"mitigates":[134],"unstable":[135],"varying":[136],"heterogeneity":[143],"among":[144],"clients.":[146],"For":[147],"point":[160,188],"used":[162],"tune":[164],"weight":[167],"term":[172],"This":[177],"avoid":[179],"meaningless":[180],"caused":[183],"out-of-date":[186],"gradient.":[189],"We":[190],"theoretically":[191],"prove":[192],"that":[193,216],"our":[194,217],"achieve":[197,221],"linear":[199],"speedup":[200],"$\\mathcal":[203],"{O}(\\frac{1}{\\sqrt{SKT}})$O(1SKT)":[204],"non-convex":[206],"objective":[207],"functions":[208],"under":[209],"partial":[210],"client":[211],"participation.":[212],"Extensive":[213],"experiments":[214],"demonstrate":[215],"proposed":[218],"method":[219],"higher":[222],"test":[223],"accuracy":[224],"than":[225],"baselines":[227],"decrease":[229],"communication":[230],"rounds":[231],"greatly.":[232]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-01-11T23:08:45.486102","created_date":"2025-10-10T00:00:00"}