{"id":"https://openalex.org/W4386472972","doi":"https://doi.org/10.1109/access.2023.3312572","title":"Enabling Large Batch Size Training for DNN Models Beyond the Memory Limit While Maintaining Performance","display_name":"Enabling Large Batch Size Training for DNN Models Beyond the Memory Limit While Maintaining Performance","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4386472972","doi":"https://doi.org/10.1109/access.2023.3312572"},"language":"en","primary_location":{"id":"doi:10.1109/access.2023.3312572","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3312572","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10242106.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10242106.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005892736","display_name":"XinYu Piao","orcid":"https://orcid.org/0009-0000-7502-4080"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Xinyu Piao","raw_affiliation_strings":["School of Electrical Engineering, Korea University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0009-0000-7502-4080","affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Korea University, Seoul, South Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030426865","display_name":"DoangJoo Synn","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Doangjoo Synn","raw_affiliation_strings":["School of Computer Science, Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100644681","display_name":"Jooyoung Park","orcid":"https://orcid.org/0000-0002-6979-9362"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jooyoung Park","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University, Jurong West, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-6979-9362","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Jurong West, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018364461","display_name":"Jong\u2010Kook Kim","orcid":"https://orcid.org/0000-0003-1828-7807"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jong-Kook Kim","raw_affiliation_strings":["School of Electrical Engineering, Korea University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0003-1828-7807","affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Korea University, Seoul, South Korea","institution_ids":["https://openalex.org/I197347611"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":1.5719,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":{"value":0.85603721,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"11","issue":null,"first_page":"102981","last_page":"102990"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9997000098228455,"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":0.9997000098228455,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.996999979019165,"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":0.9965000152587891,"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":0.8019303679466248},{"id":"https://openalex.org/keywords/batch-processing","display_name":"Batch processing","score":0.5498932003974915},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.5450587272644043},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4503530263900757}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8019303679466248},{"id":"https://openalex.org/C172658912","wikidata":"https://www.wikidata.org/wiki/Q661613","display_name":"Batch processing","level":2,"score":0.5498932003974915},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.5450587272644043},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4503530263900757},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2023.3312572","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3312572","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10242106.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:0f1f8385fbce4194adb86c8d4ead808e","is_oa":true,"landing_page_url":"https://doaj.org/article/0f1f8385fbce4194adb86c8d4ead808e","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 11, Pp 102981-102990 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2023.3312572","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3312572","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10242106.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7066427888","display_name":null,"funder_award_id":"NRF-2016R1D1A1B04933156","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386472972.pdf","grobid_xml":"https://content.openalex.org/works/W4386472972.grobid-xml"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W1598866093","https://openalex.org/W1836465849","https://openalex.org/W1901129140","https://openalex.org/W1987869189","https://openalex.org/W2009797711","https://openalex.org/W2072566913","https://openalex.org/W2108598243","https://openalex.org/W2113547287","https://openalex.org/W2132737349","https://openalex.org/W2168231600","https://openalex.org/W2194775991","https://openalex.org/W2533598788","https://openalex.org/W2757910899","https://openalex.org/W2799069271","https://openalex.org/W2953384591","https://openalex.org/W2962747323","https://openalex.org/W2962766617","https://openalex.org/W2963016543","https://openalex.org/W2963959650","https://openalex.org/W2965658867","https://openalex.org/W2969388332","https://openalex.org/W2972087877","https://openalex.org/W2991040477","https://openalex.org/W3005680577","https://openalex.org/W3037847693","https://openalex.org/W3157943880","https://openalex.org/W3160284783","https://openalex.org/W3172509117","https://openalex.org/W4295312788","https://openalex.org/W6635810480","https://openalex.org/W6638667902","https://openalex.org/W6639824700","https://openalex.org/W6676756733","https://openalex.org/W6679393576","https://openalex.org/W6684859321","https://openalex.org/W6713134421","https://openalex.org/W6744513255","https://openalex.org/W6747917562","https://openalex.org/W6750269818","https://openalex.org/W6753584990","https://openalex.org/W6756718674","https://openalex.org/W6766978945","https://openalex.org/W6774314701","https://openalex.org/W6795435739"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2591697403","https://openalex.org/W2944728705","https://openalex.org/W2904022177","https://openalex.org/W2359348847","https://openalex.org/W3011538607","https://openalex.org/W4294432981","https://openalex.org/W4321441197","https://openalex.org/W2953716828"],"abstract_inverted_index":{"Recent":[0],"deep":[1,122,180],"learning":[2,123,181],"models":[3,124,182],"are":[4],"difficult":[5],"to":[6,21,115,125,168,178,183],"train":[7,126,184],"using":[8,185,203],"a":[9,27,109,129,135,138,157,195],"large":[10,28],"batch":[11,30,33,61,95,130,136,187],"size,":[12],"because":[13,59,85],"commodity":[14],"machines":[15],"may":[16],"not":[17],"have":[18],"enough":[19],"memory":[20,57,69,103,146,192,200],"accommodate":[22],"both":[23],"the":[24,38,42,54,60,67,71,76,94,101,144,153,163,170,191,199],"model":[25,72],"and":[26,45,50,147],"data":[29,77,88],"size.":[31],"The":[32,172],"size":[34,62,79,90,96,139,201],"is":[35,47,51,73,80,91,166,177],"one":[36],"of":[37,174,194],"hyper-parameters":[39],"used":[40,167],"in":[41,143],"training":[43],"model,":[44],"it":[46],"dependent":[48],"on":[49,162],"limited":[52],"by":[53,127],"target":[55],"machine":[56],"capacity":[58,193],"can":[63,98,141],"only":[64],"fit":[65,99,142],"into":[66,100,137],"remaining":[68,102,145],"after":[70],"uploaded.":[74],"Moreover,":[75],"item":[78,89],"also":[81],"an":[82],"important":[83],"factor":[84],"if":[86],"each":[87],"larger":[92,186],"then":[93],"that":[97,133,140,189],"becomes":[104],"smaller.":[105],"This":[106,119],"paper":[107],"proposes":[108],"method":[110,120,132,176],"called":[111],"Micro-Batch":[112],"Processing":[113],"(MBP)":[114],"address":[116],"this":[117],"problem.":[118],"helps":[121],"providing":[128],"processing":[131,152],"splits":[134],"processes":[148],"them":[149],"sequentially.":[150],"After":[151],"small":[154],"batches":[155],"individually,":[156],"loss":[158],"normalization":[159],"algorithm":[160],"based":[161],"gradient":[164],"accumulation":[165],"maintain":[169],"performance.":[171],"purpose":[173],"our":[175],"allow":[179],"sizes":[188],"exceed":[190],"system":[196],"without":[197],"increasing":[198],"or":[202],"multiple":[204],"devices":[205],"(GPUs).":[206]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2023-09-07T00:00:00"}