{"id":"https://openalex.org/W2965726917","doi":"https://doi.org/10.24963/ijcai.2019/363","title":"Learning to Learn Gradient Aggregation by Gradient Descent","display_name":"Learning to Learn Gradient Aggregation by Gradient Descent","publication_year":2019,"publication_date":"2019-07-28","ids":{"openalex":"https://openalex.org/W2965726917","doi":"https://doi.org/10.24963/ijcai.2019/363","mag":"2965726917"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2019/363","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/363","pdf_url":"https://www.ijcai.org/proceedings/2019/0363.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2019/0363.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023003327","display_name":"Jinlong Ji","orcid":"https://orcid.org/0000-0001-8348-4394"},"institutions":[{"id":"https://openalex.org/I58956616","display_name":"Case Western Reserve University","ror":"https://ror.org/051fd9666","country_code":"US","type":"education","lineage":["https://openalex.org/I58956616"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinlong Ji","raw_affiliation_strings":["Case Western Reserve University"],"affiliations":[{"raw_affiliation_string":"Case Western Reserve University","institution_ids":["https://openalex.org/I58956616"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100773787","display_name":"Xuhui Chen","orcid":"https://orcid.org/0009-0003-3444-1226"},"institutions":[{"id":"https://openalex.org/I58956616","display_name":"Case Western Reserve University","ror":"https://ror.org/051fd9666","country_code":"US","type":"education","lineage":["https://openalex.org/I58956616"]},{"id":"https://openalex.org/I149910238","display_name":"Kent State University","ror":"https://ror.org/049pfb863","country_code":"US","type":"education","lineage":["https://openalex.org/I149910238"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xuhui Chen","raw_affiliation_strings":["Case Western Reserve University","Kent State University"],"affiliations":[{"raw_affiliation_string":"Case Western Reserve University","institution_ids":["https://openalex.org/I58956616"]},{"raw_affiliation_string":"Kent State University","institution_ids":["https://openalex.org/I149910238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075121594","display_name":"Qianlong Wang","orcid":"https://orcid.org/0000-0002-4238-4909"},"institutions":[{"id":"https://openalex.org/I58956616","display_name":"Case Western Reserve University","ror":"https://ror.org/051fd9666","country_code":"US","type":"education","lineage":["https://openalex.org/I58956616"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qianlong Wang","raw_affiliation_strings":["Case Western Reserve University"],"affiliations":[{"raw_affiliation_string":"Case Western Reserve University","institution_ids":["https://openalex.org/I58956616"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091486269","display_name":"Lixing Yu","orcid":"https://orcid.org/0000-0003-0333-2476"},"institutions":[{"id":"https://openalex.org/I58956616","display_name":"Case Western Reserve University","ror":"https://ror.org/051fd9666","country_code":"US","type":"education","lineage":["https://openalex.org/I58956616"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lixing Yu","raw_affiliation_strings":["Case Western Reserve University"],"affiliations":[{"raw_affiliation_string":"Case Western Reserve University","institution_ids":["https://openalex.org/I58956616"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100455171","display_name":"Pan Li","orcid":"https://orcid.org/0000-0001-6522-2446"},"institutions":[{"id":"https://openalex.org/I58956616","display_name":"Case Western Reserve University","ror":"https://ror.org/051fd9666","country_code":"US","type":"education","lineage":["https://openalex.org/I58956616"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pan Li","raw_affiliation_strings":["Case Western Reserve University"],"affiliations":[{"raw_affiliation_string":"Case Western Reserve University","institution_ids":["https://openalex.org/I58956616"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100773787"],"corresponding_institution_ids":["https://openalex.org/I149910238","https://openalex.org/I58956616"],"apc_list":null,"apc_paid":null,"fwci":1.9602,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.89746134,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2614","last_page":"2620"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9994999766349792,"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":0.9994999766349792,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9993000030517578,"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":0.9990000128746033,"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/news-aggregator","display_name":"News aggregator","score":0.918079137802124},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8098855018615723},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7445008754730225},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.6229251623153687},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5977972745895386},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5930825471878052},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.5596762299537659},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.49809956550598145},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.47866711020469666},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.4375841021537781},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.43473315238952637},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.43352073431015015},{"id":"https://openalex.org/keywords/byzantine-fault-tolerance","display_name":"Byzantine fault tolerance","score":0.42816802859306335},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.3994457721710205},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.36001187562942505},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.10029581189155579}],"concepts":[{"id":"https://openalex.org/C180505990","wikidata":"https://www.wikidata.org/wiki/Q498267","display_name":"News aggregator","level":2,"score":0.918079137802124},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8098855018615723},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7445008754730225},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.6229251623153687},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5977972745895386},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5930825471878052},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.5596762299537659},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.49809956550598145},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47866711020469666},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.4375841021537781},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.43473315238952637},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.43352073431015015},{"id":"https://openalex.org/C168021876","wikidata":"https://www.wikidata.org/wiki/Q1353446","display_name":"Byzantine fault tolerance","level":3,"score":0.42816802859306335},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.3994457721710205},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.36001187562942505},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.10029581189155579},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2019/363","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/363","pdf_url":"https://www.ijcai.org/proceedings/2019/0363.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2019/363","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/363","pdf_url":"https://www.ijcai.org/proceedings/2019/0363.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5600000023841858,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2965726917.pdf","grobid_xml":"https://content.openalex.org/works/W2965726917.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W778657980","https://openalex.org/W1542791059","https://openalex.org/W1598377843","https://openalex.org/W1868018859","https://openalex.org/W1924770834","https://openalex.org/W1978690136","https://openalex.org/W2018985672","https://openalex.org/W2044212084","https://openalex.org/W2064675550","https://openalex.org/W2086161653","https://openalex.org/W2116612304","https://openalex.org/W2131762048","https://openalex.org/W2154834860","https://openalex.org/W2168231600","https://openalex.org/W2186926886","https://openalex.org/W2263253503","https://openalex.org/W2606068338","https://openalex.org/W2624086852","https://openalex.org/W2752689052","https://openalex.org/W2766371994","https://openalex.org/W2787387965","https://openalex.org/W2804165311","https://openalex.org/W2914212774","https://openalex.org/W2953384591","https://openalex.org/W2963773265","https://openalex.org/W2963775850","https://openalex.org/W2963804082","https://openalex.org/W2963903325","https://openalex.org/W3146630864","https://openalex.org/W4295264816","https://openalex.org/W4297687186"],"related_works":["https://openalex.org/W4206903459","https://openalex.org/W2754816816","https://openalex.org/W4366280654","https://openalex.org/W3160167280","https://openalex.org/W4231621013","https://openalex.org/W4362706668","https://openalex.org/W3008318776","https://openalex.org/W1977633006","https://openalex.org/W1971945429","https://openalex.org/W2041416246"],"abstract_inverted_index":{"In":[0,27,174],"the":[1,42,46,61,70,73,87,97,101,121,130,133,160,164,166,180,192],"big":[2],"data":[3,19],"era,":[4],"distributed":[5,24,50,105,153,195],"machine":[6,106],"learning":[7,12,32,43,107],"emerges":[8],"as":[9],"an":[10,111],"important":[11],"paradigm":[13],"to":[14,33,40,66,68,85,95,119,128,151,182],"mine":[15],"large":[16],"volumes":[17],"of":[18,23,49,132,194],"by":[20,31,172],"taking":[21],"advantage":[22],"computing":[25],"resources.":[26],"this":[28],"work,":[29],"motivated":[30],"learn,":[34],"we":[35,53,109],"propose":[36,110],"a":[37,55,79],"meta-learning":[38],"approach":[39],"coordinate":[41],"process":[44],"in":[45,60,104],"master-slave":[47],"type":[48],"systems.":[51,154],"Specifically,":[52],"utilize":[54],"recurrent":[56],"neural":[57,88],"network":[58,89],"(RNN)":[59],"parameter":[62],"server":[63,181],"(the":[64,75],"master)":[65],"learn":[67],"aggregate":[69,183],"gradients":[71,184],"from":[72,185],"workers":[74],"slaves).":[76],"We":[77,124],"design":[78],"coordinatewise":[80],"preprocessing":[81],"and":[82,136,145],"postprocessing":[83],"method":[84],"make":[86],"based":[90],"aggregator":[91,113,162,178],"more":[92],"robust.":[93],"Besides,":[94],"address":[96],"fault":[98,168],"tolerance,":[99],"especially":[100],"Byzantine":[102,158],"attack,":[103],"systems,":[108],"RNN":[112,134,177],"with":[114],"additional":[115],"loss":[116],"information":[117],"(ARNN)":[118],"improve":[120,191],"system":[122],"resilience.":[123],"conduct":[125],"extensive":[126],"experiments":[127],"demonstrate":[129],"effectiveness":[131],"aggregator,":[135],"also":[137],"show":[138],"that":[139],"it":[140],"can":[141],"be":[142],"easily":[143],"generalized":[144],"achieve":[146],"remarkable":[147],"performance":[148],"when":[149],"transferred":[150],"other":[152],"Moreover,":[155],"under":[156],"majoritarian":[157],"attacks,":[159],"ARNN":[161],"outperforms":[163],"Krum,":[165],"state-of-art":[167],"tolerance":[169],"aggregation":[170],"method,":[171],"43.14%.":[173],"addition,":[175],"our":[176],"enables":[179],"variant":[186],"local":[187],"models,":[188],"which":[189],"significantly":[190],"scalability":[193],"learning.":[196]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}