{"id":"https://openalex.org/W3199451663","doi":"https://doi.org/10.1109/ijcnn52387.2021.9533708","title":"Two-Dimensional Learning Rate Decay: Towards Accurate Federated Learning with Non-IID Data","display_name":"Two-Dimensional Learning Rate Decay: Towards Accurate Federated Learning with Non-IID Data","publication_year":2021,"publication_date":"2021-07-18","ids":{"openalex":"https://openalex.org/W3199451663","doi":"https://doi.org/10.1109/ijcnn52387.2021.9533708","mag":"3199451663"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn52387.2021.9533708","doi":"https://doi.org/10.1109/ijcnn52387.2021.9533708","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9533708","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"International Joint Conference on Neural Networks (IJCNN)","issn_l":"2161-4407","issn":["2161-4407"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"volume":null,"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/A5072054230","display_name":"Kaiwei Mo","orcid":"https://orcid.org/0000-0003-1111-206X","observed_orcids":["https://orcid.org/0000-0003-1111-206X"]},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Kaiwei Mo","raw_affiliation_strings":["City University of Hong Kong, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"City University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100418393","display_name":"Chen Chen","orcid":"https://orcid.org/0000-0001-9480-5632","observed_orcids":["https://orcid.org/0000-0001-9480-5632"]},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Chen","raw_affiliation_strings":["Theory Lab, Huawei HK, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Theory Lab, Huawei HK, Hong Kong, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100730410","display_name":"Jiamin Li","orcid":"https://orcid.org/0000-0001-8110-2436","observed_orcids":["https://orcid.org/0000-0001-8110-2436"]},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jiamin Li","raw_affiliation_strings":["City University of Hong Kong, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"City University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084983727","display_name":"Hong Xu","orcid":"https://orcid.org/0000-0001-7874-4518","observed_orcids":["https://orcid.org/0000-0001-7874-4518"]},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Hong Xu","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101441768","display_name":"Chun Jason Xue","orcid":"https://orcid.org/0000-0002-6431-9868","observed_orcids":["https://orcid.org/0000-0002-6431-9868","https://orcid.org/0000-0002-9359-9571"]},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Chun Jason Xue","raw_affiliation_strings":["City University of Hong Kong, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"City University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.231,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.45620325,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9976000189781189,"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":0.9976000189781189,"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":0.0019000000320374966,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":9.999999747378752e-05,"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":0.9909999966621399},{"id":"https://openalex.org/keywords/non-iid-data","display_name":"non-IID data","score":0.9229999780654907},{"id":"https://openalex.org/keywords/learning-rate-decay","display_name":"learning rate decay","score":0.9739999771118164},{"id":"https://openalex.org/keywords/adaptive-learning-rate","display_name":"adaptive learning rate","score":0.7739999890327454},{"id":"https://openalex.org/keywords/communication-overhead","display_name":"communication overhead","score":0.5950000286102295},{"id":"https://openalex.org/keywords/model-convergence","display_name":"model convergence","score":0.36399999260902405}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7663167119026184},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.7232638597488403},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.6794732809066772},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6478234529495239},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.6281786561012268},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5188385248184204},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49642688035964966},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.47470822930336},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47160062193870544},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.33587801456451416},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11316010355949402},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.10189267992973328},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn52387.2021.9533708","doi":"https://doi.org/10.1109/ijcnn52387.2021.9533708","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9533708","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"International Joint Conference on Neural Networks (IJCNN)","issn_l":"2161-4407","issn":["2161-4407"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2003163868","https://openalex.org/W2116612304","https://openalex.org/W2170240176","https://openalex.org/W2416173357","https://openalex.org/W2535838896","https://openalex.org/W2541884796","https://openalex.org/W2734358244","https://openalex.org/W2797583228","https://openalex.org/W2798710209","https://openalex.org/W2798720628","https://openalex.org/W2807006176","https://openalex.org/W2896404430","https://openalex.org/W2903471046","https://openalex.org/W2914328083","https://openalex.org/W2917830734","https://openalex.org/W2946573451","https://openalex.org/W2955213239","https://openalex.org/W2963318081","https://openalex.org/W2972570881","https://openalex.org/W3016839154","https://openalex.org/W4239510810","https://openalex.org/W6750665317"],"related_works":["https://openalex.org/W4411866782","https://openalex.org/W3184838508","https://openalex.org/W4386875986","https://openalex.org/W4361230999","https://openalex.org/W4388723284","https://openalex.org/W3130968919","https://openalex.org/W4285048701","https://openalex.org/W4283329472","https://openalex.org/W7164847853","https://openalex.org/W7171785969"],"abstract_inverted_index":{"In":[0,53],"federated":[1],"learning":[2,80,98,103,138],"a":[3,14,109,134],"global":[4],"model":[5,51,74,90],"is":[6,133],"trained":[7],"with":[8,112],"training":[9,39],"data":[10,40],"geographically":[11],"distributed":[12],"over":[13,23],"number":[15],"of":[16,105,126,130],"clients.":[17],"To":[18],"reduce":[19],"the":[20,24,38,48,73,79,89,97,102,124,127,154],"communication":[21],"cost":[22],"expensive":[25],"wide":[26],"area":[27],"network,":[28],"clients":[29],"complete":[30],"multiple":[31],"local":[32,106],"iterations":[33,107],"before":[34],"synchronization.":[35],"However,":[36],"since":[37],"are":[41],"non-iid,":[42],"such":[43],"infrequent":[44],"synchronization":[45,110],"would":[46],"compromise":[47],"accuracy":[49],"after":[50],"convergence.":[52],"order":[54],"to":[55,71,153],"tackle":[56],"this":[57,67],"problem,":[58],"we":[59,94,121],"propose":[60],"Two-Dimensional":[61],"Learning":[62],"Rate":[63],"Decay":[64],"(2D-LRD)":[65],"in":[66,108],"paper,":[68],"which":[69],"aims":[70],"improve":[72],"performance":[75],"by":[76],"adaptively":[77],"tuning":[78],"rate":[81,99,139],"on":[82,116],"two":[83],"dimensions:":[84],"round-dimension":[85],"and":[86,100,119,144],"iteration-dimension":[87],"during":[88],"training.":[91],"That":[92],"is,":[93],"gradually":[95],"decrease":[96,101],"rates":[104],"round":[111,131],"different":[113],"speeds.":[114],"Based":[115],"our":[117],"experiments":[118],"analysis,":[120],"find":[122],"that":[123,146],"sum":[125],"inner":[128],"product":[129],"updates":[132],"valuable":[135],"signal":[136],"for":[137],"tuning.":[140],"We":[141],"perform":[142],"evaluation":[143],"demonstrate":[145],"2D-LRD":[147],"can":[148],"make":[149],"great":[150],"progress":[151],"compared":[152],"baseline":[155],"scheme.":[156]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2026-10-26T11:51:55.731654","created_date":"2021-09-27T00:00:00"}