{"id":"https://openalex.org/W4391382590","doi":"https://doi.org/10.1109/mwscas57524.2023.10405843","title":"A Hierarchical Communication Algorithm for Distributed Deep Learning Training","display_name":"A Hierarchical Communication Algorithm for Distributed Deep Learning Training","publication_year":2023,"publication_date":"2023-08-06","ids":{"openalex":"https://openalex.org/W4391382590","doi":"https://doi.org/10.1109/mwscas57524.2023.10405843"},"language":"en","primary_location":{"id":"doi:10.1109/mwscas57524.2023.10405843","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/mwscas57524.2023.10405843","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 66th International Midwest Symposium on Circuits and Systems (MWSCAS)","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/A5100324170","display_name":"Jiayu Zhang","orcid":"https://orcid.org/0009-0007-7658-0370"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiayu Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Microelectronics and Nanoscience,Shanghai,China","Department of Microelectronics and Nanoscience, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Microelectronics and Nanoscience,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Microelectronics and Nanoscience, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102209243","display_name":"Shaojun Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaojun Cheng","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Microelectronics and Nanoscience,Shanghai,China","Department of Microelectronics and Nanoscience, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Microelectronics and Nanoscience,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Microelectronics and Nanoscience, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041040327","display_name":"Feng Dong","orcid":"https://orcid.org/0000-0001-5085-2277"},"institutions":[{"id":"https://openalex.org/I4210115040","display_name":"iQIYI (China)","ror":"https://ror.org/026xvz038","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210115040"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Dong","raw_affiliation_strings":["Beijing iQIYI Science & Technology Co., Ltd.,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Beijing iQIYI Science & Technology Co., Ltd.,Shanghai,China","institution_ids":["https://openalex.org/I4210115040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100452017","display_name":"Ke Chen","orcid":"https://orcid.org/0000-0003-0433-5580"},"institutions":[{"id":"https://openalex.org/I4210115040","display_name":"iQIYI (China)","ror":"https://ror.org/026xvz038","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210115040"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ke Chen","raw_affiliation_strings":["Beijing iQIYI Science & Technology Co., Ltd.,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Beijing iQIYI Science & Technology Co., Ltd.,Shanghai,China","institution_ids":["https://openalex.org/I4210115040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100569623","display_name":"Yong Qiao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210115040","display_name":"iQIYI (China)","ror":"https://ror.org/026xvz038","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210115040"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Qiao","raw_affiliation_strings":["Beijing iQIYI Science & Technology Co., Ltd.,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Beijing iQIYI Science & Technology Co., Ltd.,Shanghai,China","institution_ids":["https://openalex.org/I4210115040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103236320","display_name":"Zhigang Mao","orcid":"https://orcid.org/0000-0001-9431-9853"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhigang Mao","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Microelectronics and Nanoscience,Shanghai,China","Department of Microelectronics and Nanoscience, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Microelectronics and Nanoscience,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Microelectronics and Nanoscience, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008057183","display_name":"Jianfei Jiang","orcid":"https://orcid.org/0000-0002-5521-6197"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianfei Jiang","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Microelectronics and Nanoscience,Shanghai,China","Department of Microelectronics and Nanoscience, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Microelectronics and Nanoscience,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Microelectronics and Nanoscience, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100324170"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19703336,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"abs/1706.02677","issue":null,"first_page":"526","last_page":"530"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9987000226974487,"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/T12702","display_name":"Brain Tumor Detection and Classification","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.871623158454895},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6460486054420471},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6435918211936951},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.6316424608230591},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6094324588775635},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5739622116088867},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5539558529853821},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.47270700335502625},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4616827368736267},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3391711115837097},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.30338501930236816},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.21923285722732544}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.871623158454895},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6460486054420471},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6435918211936951},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.6316424608230591},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6094324588775635},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5739622116088867},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5539558529853821},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.47270700335502625},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4616827368736267},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3391711115837097},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.30338501930236816},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.21923285722732544},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mwscas57524.2023.10405843","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/mwscas57524.2023.10405843","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 66th International Midwest Symposium on Circuits and Systems (MWSCAS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2622263826","https://openalex.org/W2896457183","https://openalex.org/W2963179579","https://openalex.org/W3086105743","https://openalex.org/W4226057994","https://openalex.org/W6684191040","https://openalex.org/W6739622702","https://openalex.org/W6746200960","https://openalex.org/W6751193408","https://openalex.org/W6758557334"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2146343568","https://openalex.org/W98480971","https://openalex.org/W17155033","https://openalex.org/W2891987081","https://openalex.org/W2168758875","https://openalex.org/W4246549241","https://openalex.org/W2410733619","https://openalex.org/W2963483475"],"abstract_inverted_index":{"Distributed":[0],"deep":[1,34,39,130],"learning":[2,35,40,131],"training":[3,41],"nowadays":[4],"has":[5],"become":[6],"an":[7],"important":[8],"workload":[9],"on":[10,102,128],"data":[11],"center":[12],"GPU":[13],"clusters.":[14],"However,":[15],"in":[16],"some":[17],"cases,":[18],"the":[19],"inter-node":[20,70],"bandwidth":[21],"is":[22],"limited":[23],"(e.g.,":[24],"20Gbps)":[25],"and":[26,59,71,84,133],"thus":[27],"becomes":[28],"a":[29,51,76,96,103],"performance":[30,97],"bottleneck":[31],"for":[32],"existing":[33,125],"systems":[36,127],"to":[37,64,88,121],"scale":[38],"across":[42],"multiple":[43],"nodes.":[44],"To":[45],"exploit":[46],"this":[47],"insight,":[48],"we":[49,94],"propose":[50],"hierarchical":[52],"communication":[53,91],"algorithm":[54,101,118],"combined":[55],"with":[56,108],"Asynchronous":[57],"SGD":[58,61],"Synchronous":[60],"named":[62],"AS-SGD":[63],"make":[65],"full":[66],"use":[67],"of":[68,78,99],"both":[69],"intra-node":[72],"network":[73],"bandwidth.":[74],"Moreover,":[75],"set":[77],"system":[79],"optimization":[80],"techniques":[81],"like":[82],"quantization":[83],"decentralization":[85],"are":[86],"applied":[87],"further":[89],"reduce":[90],"costs.":[92],"Finally,":[93],"present":[95],"evaluation":[98],"our":[100,117],"4-node":[104],"cluster":[105],"(each":[106],"node":[107],"8":[109],"Nvidia":[110],"Tesla":[111],"V100":[112],"GPUs).":[113],"Experiments":[114],"show":[115],"that":[116],"achieves":[119],"up":[120],"4.95X":[122],"speedup":[123],"than":[124],"state-of-the-art":[126],"popular":[129],"models":[132],"datasets.":[134]},"counts_by_year":[],"updated_date":"2025-12-25T23:11:45.687758","created_date":"2025-10-10T00:00:00"}