{"id":"https://openalex.org/W4312983671","doi":"https://doi.org/10.14778/3561261.3561265","title":"MiCS","display_name":"MiCS","publication_year":2022,"publication_date":"2022-09-01","ids":{"openalex":"https://openalex.org/W4312983671","doi":"https://doi.org/10.14778/3561261.3561265"},"language":"en","primary_location":{"id":"doi:10.14778/3561261.3561265","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3561261.3561265","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-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/A5100390145","display_name":"Zhen Zhang","orcid":"https://orcid.org/0000-0001-8448-5663"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhen Zhang","raw_affiliation_strings":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042419001","display_name":"Shuai Zheng","orcid":"https://orcid.org/0000-0001-8560-8135"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuai Zheng","raw_affiliation_strings":["Amazon Web Services"],"affiliations":[{"raw_affiliation_string":"Amazon Web Services","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101638214","display_name":"Yida Wang","orcid":"https://orcid.org/0000-0001-8165-840X"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yida Wang","raw_affiliation_strings":["Amazon Web Services"],"affiliations":[{"raw_affiliation_string":"Amazon Web Services","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107936883","display_name":"Justin Chiu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Justin Chiu","raw_affiliation_strings":["Amazon"],"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082384108","display_name":"George Karypis","orcid":"https://orcid.org/0000-0003-2753-1437"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"George Karypis","raw_affiliation_strings":["Amazon Web Services"],"affiliations":[{"raw_affiliation_string":"Amazon Web Services","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013670321","display_name":"Trishul Chilimbi","orcid":"https://orcid.org/0000-0001-6711-1117"},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Trishul Chilimbi","raw_affiliation_strings":["Amazon"],"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100399461","display_name":"Mu Li","orcid":"https://orcid.org/0000-0002-4433-2301"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mu Li","raw_affiliation_strings":["Amazon Web Services"],"affiliations":[{"raw_affiliation_string":"Amazon Web Services","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101828824","display_name":"Xin Jin","orcid":"https://orcid.org/0000-0002-1820-8358"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Jin","raw_affiliation_strings":["Peking University"],"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5100390145"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":1.794,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.8751429,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"16","issue":"1","first_page":"37","last_page":"50"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9933000206947327,"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":0.9933000206947327,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.991599977016449,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9887999892234802,"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/computer-science","display_name":"Computer science","score":0.7876400947570801},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.7154732942581177},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6801454424858093},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.6310961842536926},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6275293231010437},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.5657216906547546},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.5537065267562866},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5215808749198914},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.47237852215766907},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.46920743584632874},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.3408139944076538},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.13614428043365479},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12588584423065186},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.07734790444374084},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.0707443356513977}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7876400947570801},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.7154732942581177},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6801454424858093},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.6310961842536926},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6275293231010437},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.5657216906547546},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.5537065267562866},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5215808749198914},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.47237852215766907},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.46920743584632874},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.3408139944076538},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.13614428043365479},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12588584423065186},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.07734790444374084},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0707443356513977},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3561261.3561265","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3561261.3561265","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"}],"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/W398859631","https://openalex.org/W2116377381","https://openalex.org/W2131613942","https://openalex.org/W2164945803","https://openalex.org/W2407022425","https://openalex.org/W2901299405","https://openalex.org/W2966048283","https://openalex.org/W2969388332","https://openalex.org/W2975712713","https://openalex.org/W3044837714","https://openalex.org/W3081168214","https://openalex.org/W3132107458","https://openalex.org/W4212774754"],"related_works":["https://openalex.org/W2131630752","https://openalex.org/W2391167130","https://openalex.org/W2092071486","https://openalex.org/W4283067488","https://openalex.org/W2475198316","https://openalex.org/W4242952987","https://openalex.org/W2015855483","https://openalex.org/W2082747552","https://openalex.org/W2108390342","https://openalex.org/W2298102683"],"abstract_inverted_index":{"Existing":[0],"general":[1],"purpose":[2],"frameworks":[3],"for":[4,74],"gigantic":[5],"model":[6,107,130],"training,":[7],"i.e.,":[8],"dense":[9],"models":[10],"with":[11,21,131,138,160],"billions":[12],"of":[13,51,72,96,103,121,153],"parameters,":[14],"cannot":[15],"scale":[16],"efficiently":[17],"on":[18,89,135,156],"cloud":[19,159],"environment":[20],"various":[22],"networking":[23],"conditions":[24],"due":[25],"to":[26,41,100,118,126,146],"large":[27,106],"communication":[28,44,55],"overheads.":[29],"In":[30],"this":[31],"paper,":[32],"we":[33],"propose":[34],"MiCS,":[35],"which":[36,115],"Minimizes":[37],"the":[38,49,70,93,104],"Communication":[39],"Scale":[40],"bring":[42],"down":[43],"overhead.":[45,86],"Specifically,":[46],"by":[47],"decreasing":[48],"number":[50],"participants":[52],"in":[53],"a":[54,128,157],"collective,":[56],"MiCS":[57,97,110,123],"can":[58],"utilize":[59],"heterogeneous":[60],"network":[61,64,77],"bandwidth,":[62],"reduce":[63,69],"traffic":[65],"over":[66,148],"slower":[67],"links,":[68],"latency":[71],"communications":[73],"maintaining":[75],"high":[76],"bandwidth":[78],"utilization,":[79],"and":[80,142,164],"amortize":[81],"expensive":[82],"global":[83],"gradient":[84],"synchronization":[85],"Our":[87],"evaluation":[88],"AWS":[90],"shows":[91],"that":[92,102,120],"system":[94],"throughput":[95],"is":[98,116,144],"up":[99,117],"2.89\u00d7":[101],"state-of-the-art":[105],"training":[108],"systems.":[109],"achieves":[111],"near-linear":[112],"scaling":[113],"efficiency,":[114,141],"1.27\u00d7":[119],"DeepSpeed.":[122],"allows":[124],"us":[125],"train":[127],"proprietary":[129],"100":[132],"billion":[133],"parameters":[134],"512":[136],"GPUs":[137],"99.4%":[139],"weak-scaling":[140],"it":[143],"able":[145],"saturate":[147],"54.5%":[149],"theoretical":[150],"computation":[151],"power":[152],"each":[154],"GPU":[155,162],"public":[158],"less":[161],"memory":[163],"more":[165],"restricted":[166],"networks":[167],"than":[168],"DGX-A100":[169],"clusters.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4}],"updated_date":"2026-03-25T14:56:36.534964","created_date":"2023-01-05T00:00:00"}