{"id":"https://openalex.org/W4399574191","doi":"https://doi.org/10.1109/isorc61049.2024.10551324","title":"Hierarchical Heterogeneous Cluster Systems for Scalable Distributed Deep Learning","display_name":"Hierarchical Heterogeneous Cluster Systems for Scalable Distributed Deep Learning","publication_year":2024,"publication_date":"2024-05-22","ids":{"openalex":"https://openalex.org/W4399574191","doi":"https://doi.org/10.1109/isorc61049.2024.10551324"},"language":"en","primary_location":{"id":"doi:10.1109/isorc61049.2024.10551324","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/isorc61049.2024.10551324","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 27th International Symposium on Real-Time Distributed Computing (ISORC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://escholarship.org/content/qt84n5978r/qt84n5978r.pdf?t=s8dox4","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100354963","display_name":"Yibo Wang","orcid":"https://orcid.org/0000-0001-8872-1811"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yibo Wang","raw_affiliation_strings":["University of California, Irvine,Electrical Engineering and Computer Science,Irvine,USA","Electrical Engineering and Computer Science, University of California, Irvine, Irvine, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Irvine,Electrical Engineering and Computer Science,Irvine,USA","institution_ids":["https://openalex.org/I204250578"]},{"raw_affiliation_string":"Electrical Engineering and Computer Science, University of California, Irvine, Irvine, USA","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074649403","display_name":"Tongsheng Geng","orcid":null},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tongsheng Geng","raw_affiliation_strings":["University of California, Irvine,Electrical Engineering and Computer Science,Irvine,USA","Electrical Engineering and Computer Science, University of California, Irvine, Irvine, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Irvine,Electrical Engineering and Computer Science,Irvine,USA","institution_ids":["https://openalex.org/I204250578"]},{"raw_affiliation_string":"Electrical Engineering and Computer Science, University of California, Irvine, Irvine, USA","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007449090","display_name":"E. L. R. da Silva","orcid":"https://orcid.org/0000-0002-0407-5806"},"institutions":[{"id":"https://openalex.org/I170935008","display_name":"Pontif\u00edcia Universidade Cat\u00f3lica de Minas Gerais","ror":"https://ror.org/03j1rr444","country_code":"BR","type":"education","lineage":["https://openalex.org/I170935008"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Ericson Silva","raw_affiliation_strings":["Pontifical Catholic University of Minas Gerais,Electrical Engineering and Computer Science,Minas Gerais,Brazil","Electrical Engineering and Computer Science, Pontifical Catholic University of Minas Gerais, Minas Gerais, Brazil"],"affiliations":[{"raw_affiliation_string":"Pontifical Catholic University of Minas Gerais,Electrical Engineering and Computer Science,Minas Gerais,Brazil","institution_ids":["https://openalex.org/I170935008"]},{"raw_affiliation_string":"Electrical Engineering and Computer Science, Pontifical Catholic University of Minas Gerais, Minas Gerais, Brazil","institution_ids":["https://openalex.org/I170935008"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019948826","display_name":"Jean\u2010Luc Gaudiot","orcid":"https://orcid.org/0000-0001-9164-8731"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jean-Luc Gaudiot","raw_affiliation_strings":["University of California, Irvine,Electrical Engineering and Computer Science,Irvine,USA","Electrical Engineering and Computer Science, University of California, Irvine, Irvine, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Irvine,Electrical Engineering and Computer Science,Irvine,USA","institution_ids":["https://openalex.org/I204250578"]},{"raw_affiliation_string":"Electrical Engineering and Computer Science, University of California, Irvine, Irvine, USA","institution_ids":["https://openalex.org/I204250578"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100354963"],"corresponding_institution_ids":["https://openalex.org/I204250578"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06606317,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"25","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9911999702453613,"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":0.9911999702453613,"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/T10320","display_name":"Neural Networks and Applications","score":0.9835000038146973,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.982200026512146,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7790170907974243},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.707256019115448},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.6565341949462891},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5541359186172485},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3636828660964966},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.34150058031082153},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.278054416179657},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.11364829540252686}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7790170907974243},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.707256019115448},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.6565341949462891},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5541359186172485},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3636828660964966},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.34150058031082153},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.278054416179657},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.11364829540252686}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/isorc61049.2024.10551324","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/isorc61049.2024.10551324","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 27th International Symposium on Real-Time Distributed Computing (ISORC)","raw_type":"proceedings-article"},{"id":"pmh:oai:escholarship.org:ark:/13030/qt84n5978r","is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/84n5978r","pdf_url":"https://escholarship.org/content/qt84n5978r/qt84n5978r.pdf?t=s8dox4","source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"etd"}],"best_oa_location":{"id":"pmh:oai:escholarship.org:ark:/13030/qt84n5978r","is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/84n5978r","pdf_url":"https://escholarship.org/content/qt84n5978r/qt84n5978r.pdf?t=s8dox4","source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"etd"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399574191.pdf","grobid_xml":"https://content.openalex.org/works/W4399574191.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W2168231600","https://openalex.org/W2581760236","https://openalex.org/W2603020828","https://openalex.org/W2955013293","https://openalex.org/W2957938647","https://openalex.org/W2994144272","https://openalex.org/W3004495293","https://openalex.org/W3041089513","https://openalex.org/W3102606411","https://openalex.org/W3195968870","https://openalex.org/W4301239768","https://openalex.org/W6636806777","https://openalex.org/W6684859321","https://openalex.org/W6713134421","https://openalex.org/W6748645090","https://openalex.org/W6789216674"],"related_works":["https://openalex.org/W2389214306","https://openalex.org/W4235240664","https://openalex.org/W2965083567","https://openalex.org/W1982914007","https://openalex.org/W2159583675","https://openalex.org/W1824242903","https://openalex.org/W1493858311","https://openalex.org/W2155470929","https://openalex.org/W2394465510","https://openalex.org/W2111125783"],"abstract_inverted_index":{"Distributed":[0],"deep":[1,17,93],"learning":[2,18],"framework":[3,34],"tools":[4],"should":[5,70],"aim":[6],"at":[7],"high":[8],"efficiency":[9],"of":[10,14,44,58,97,119],"training":[11],"and":[12,30,47,50,103,123,133],"inference":[13],"distributed":[15,92,111],"exascale":[16],"algorithms.":[19],"There":[20],"are":[21],"three":[22],"major":[23],"challenges":[24],"in":[25],"this":[26],"endeavor:":[27],"scalability,":[28],"adaptivity":[29],"efficiency.":[31],"Any":[32],"future":[33],"will":[35,51],"need":[36],"to":[37,55,65,127],"be":[38,53,56,71],"adaptively":[39],"utilized":[40],"for":[41,91],"a":[42,85],"variety":[43],"heterogeneous":[45],"hardware":[46],"network":[48],"environments":[49],"thus":[52],"required":[54],"capable":[57],"scaling":[59],"from":[60],"single":[61],"compute":[62,120,129],"node":[63],"up":[64],"large":[66],"clusters.":[67],"Further,":[68],"it":[69],"efficiently":[72],"integrated":[73],"into":[74],"popular":[75],"frameworks":[76],"such":[77],"as":[78,116],"TensorFlow,":[79],"PyTorch,":[80],"etc.":[81],"This":[82],"paper":[83],"proposes":[84],"dynamically":[86],"hybrid":[87],"(hierarchy)":[88],"distribution":[89],"structure":[90],"learning,":[94],"taking":[95],"advantage":[96],"flexible":[98],"synchronization":[99],"on":[100,110],"both":[101],"centralized":[102],"decentralized":[104],"architectures,":[105],"implementing":[106],"multi-level":[107],"fine-grain":[108],"parallelism":[109],"platforms.":[112],"It":[113],"is":[114],"scalable":[115],"the":[117],"number":[118],"nodes":[121],"increases,":[122],"can":[124],"also":[125],"adapt":[126],"various":[128],"abilities,":[130],"memory":[131],"structures":[132],"communication":[134],"costs.":[135]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}