{"id":"https://openalex.org/W4416252304","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228326","title":"Improving Communication-Efficient and Byzantine-Robust Distributed Learning with Local Adaptive Momentum","display_name":"Improving Communication-Efficient and Byzantine-Robust Distributed Learning with Local Adaptive Momentum","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416252304","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228326"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11228326","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228326","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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/A5100448724","display_name":"Yonghui Li","orcid":"https://orcid.org/0000-0001-7702-1123"},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]},{"id":"https://openalex.org/I4210125143","display_name":"Chengdu University","ror":"https://ror.org/034z67559","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210125143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanghao Li","raw_affiliation_strings":["Sichuan University,College of Computer Science,Chengdu,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sichuan University,College of Computer Science,Chengdu,China","institution_ids":["https://openalex.org/I4210125143","https://openalex.org/I24185976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101594202","display_name":"Changxin Liu","orcid":"https://orcid.org/0000-0002-0819-5303"},"institutions":[{"id":"https://openalex.org/I143593769","display_name":"East China University of Science and Technology","ror":"https://ror.org/01vyrm377","country_code":"CN","type":"education","lineage":["https://openalex.org/I143593769"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changxin Liu","raw_affiliation_strings":["East China University of Science and Technology,Key Laboratory of Smart Manufacturing in Energy Chemical Process, Ministry of Education,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China University of Science and Technology,Key Laboratory of Smart Manufacturing in Energy Chemical Process, Ministry of Education,Shanghai,China","institution_ids":["https://openalex.org/I143593769"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062353872","display_name":"Yuhao Yi","orcid":"https://orcid.org/0000-0001-6036-0276"},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]},{"id":"https://openalex.org/I4210125143","display_name":"Chengdu University","ror":"https://ror.org/034z67559","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210125143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhao Yi","raw_affiliation_strings":["Sichuan University,College of Computer Science,Chengdu,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sichuan University,College of Computer Science,Chengdu,China","institution_ids":["https://openalex.org/I4210125143","https://openalex.org/I24185976"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16618266,"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":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.6535000205039978,"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":0.6535000205039978,"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":0.20739999413490295,"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/T12676","display_name":"Machine Learning and ELM","score":0.036400001496076584,"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/variance-reduction","display_name":"Variance reduction","score":0.6816999912261963},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.6169000267982483},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5476999878883362},{"id":"https://openalex.org/keywords/byzantine-fault-tolerance","display_name":"Byzantine fault tolerance","score":0.5299000144004822},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.49239999055862427},{"id":"https://openalex.org/keywords/distributed-learning","display_name":"Distributed learning","score":0.44769999384880066},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.35109999775886536},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.3447999954223633}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6948000192642212},{"id":"https://openalex.org/C62644790","wikidata":"https://www.wikidata.org/wiki/Q3454689","display_name":"Variance reduction","level":3,"score":0.6816999912261963},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.6169000267982483},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5476999878883362},{"id":"https://openalex.org/C168021876","wikidata":"https://www.wikidata.org/wiki/Q1353446","display_name":"Byzantine fault tolerance","level":3,"score":0.5299000144004822},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.49239999055862427},{"id":"https://openalex.org/C2779582901","wikidata":"https://www.wikidata.org/wiki/Q21013010","display_name":"Distributed learning","level":2,"score":0.44769999384880066},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4058000147342682},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.35109999775886536},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.3447999954223633},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.3395000100135803},{"id":"https://openalex.org/C130120984","wikidata":"https://www.wikidata.org/wiki/Q2835898","display_name":"Distributed algorithm","level":2,"score":0.32989999651908875},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3287999927997589},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31949999928474426},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3188999891281128},{"id":"https://openalex.org/C125014702","wikidata":"https://www.wikidata.org/wiki/Q4680749","display_name":"Adaptive learning","level":2,"score":0.3188000023365021},{"id":"https://openalex.org/C60718061","wikidata":"https://www.wikidata.org/wiki/Q1414747","display_name":"Momentum (technical analysis)","level":2,"score":0.31119999289512634},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.3050000071525574},{"id":"https://openalex.org/C2781395549","wikidata":"https://www.wikidata.org/wiki/Q4680762","display_name":"Adaptive sampling","level":3,"score":0.2874000072479248},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2759999930858612},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26429998874664307},{"id":"https://openalex.org/C17532199","wikidata":"https://www.wikidata.org/wiki/Q17083590","display_name":"Quantum Byzantine agreement","level":4,"score":0.2558000087738037}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11228326","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228326","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322990","display_name":"Sichuan University","ror":"https://ror.org/011ashp19"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2120510885","https://openalex.org/W2153635508","https://openalex.org/W2194775991","https://openalex.org/W2809788191","https://openalex.org/W2912213068","https://openalex.org/W2979956265","https://openalex.org/W2995022099","https://openalex.org/W3022213304","https://openalex.org/W3046449784","https://openalex.org/W4213446860","https://openalex.org/W4252654521","https://openalex.org/W4381956520","https://openalex.org/W4402925050"],"related_works":[],"abstract_inverted_index":{"Due":[0],"to":[1,27,89,101,108,120,141,162,201],"increasing":[2],"interest":[3],"in":[4,87],"collaborative":[5],"and":[6,54,167],"distributed":[7,21,37],"learning,":[8,22],"there":[9],"has":[10,79],"been":[11,199],"a":[12,23,29,42,118,138],"significant":[13],"focus":[14],"on":[15],"Byzantine":[16,19,127,143,179],"robustness.":[17],"In":[18,129],"robust":[20,74],"central":[24],"server":[25],"aims":[26,107],"train":[28],"machine":[30],"learning":[31],"model":[32],"using":[33,113],"data":[34],"that":[35,145],"are":[36,172],"among":[38],"multiple":[39],"workers.":[40,180],"However,":[41],"small":[43],"percentage":[44],"of":[45,62,83,124,178,184,191,205],"these":[46],"workers":[47],"may":[48],"deviate":[49],"from":[50,93],"the":[51,81,122,158,182,188,203,206],"prescribed":[52],"algorithm":[53],"send":[55],"malicious":[56,91],"messages.":[57],"To":[58],"address":[59],"this":[60,103,110,132],"type":[61],"attacks,":[63],"resilient":[64],"training":[65],"algorithms":[66],"combine":[67],"stochastic":[68,148],"gradient":[69,85,149],"descent":[70],"(SGD)":[71],"with":[72,131,152],"various":[73],"aggregation":[75],"rules.":[76],"Previous":[77],"work":[78],"emphasized":[80],"importance":[82],"reducing":[84],"noise":[86],"SGD":[88,125],"differentiate":[90],"updates":[92],"normal":[94],"ones,":[95],"by":[96,112],"applying":[97],"variance":[98,150,165],"reduction":[99,151,166],"techniques":[100],"tackle":[102],"issue.":[104],"This":[105],"paper":[106],"advance":[109],"frontier":[111],"local":[114,159],"adaptive":[115,147,160],"momentum":[116,161],"as":[117],"means":[119],"improve":[121],"robustness":[123],"against":[126],"attacks.":[128],"line":[130],"objective,":[133],"our":[134],"study":[135],"introduces":[136],"Byz-AdaVR-EF21,":[137],"method":[139],"designed":[140],"withstand":[142],"behavior":[144],"applies":[146],"communication":[153,185],"compression.":[154],"Each":[155],"worker":[156],"calculates":[157],"simultaneously":[163],"achieve":[164],"fast":[168],"convergence.":[169],"These":[170],"features":[171],"crucial":[173],"for":[174],"more":[175,193],"effective":[176],"countering":[177],"Additionally,":[181],"use":[183],"compression":[186],"provides":[187],"added":[189],"benefit":[190],"enabling":[192],"efficient":[194],"communication.":[195],"Extensive":[196],"experiments":[197],"have":[198],"conducted":[200],"showcase":[202],"effectiveness":[204],"proposed":[207],"algorithm.":[208]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-14T00:00:00"}