{"id":"https://openalex.org/W2914240770","doi":"https://doi.org/10.1145/3293883.3295718","title":"A GPU memory efficient speed-up scheme for training ultra-deep neural networks","display_name":"A GPU memory efficient speed-up scheme for training ultra-deep neural networks","publication_year":2019,"publication_date":"2019-02-05","ids":{"openalex":"https://openalex.org/W2914240770","doi":"https://doi.org/10.1145/3293883.3295718","mag":"2914240770"},"language":"en","primary_location":{"id":"doi:10.1145/3293883.3295718","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3293883.3295718","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th Symposium on Principles and Practice of Parallel Programming","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/A5102350480","display_name":"Jinrong Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinrong Guo","raw_affiliation_strings":["Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011069823","display_name":"Wantao Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wantao Liu","raw_affiliation_strings":["Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103581056","display_name":"Wang Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang Wang","raw_affiliation_strings":["Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101304047","display_name":"Qu Lu","orcid":"https://orcid.org/0009-0004-0524-6277"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qu Lu","raw_affiliation_strings":["Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018288181","display_name":"Songlin Hu","orcid":"https://orcid.org/0000-0002-7170-3809"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Songlin Hu","raw_affiliation_strings":["Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112539471","display_name":"Jizhong Han","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jizhong Han","raw_affiliation_strings":["Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039670436","display_name":"Ruixuan Li","orcid":"https://orcid.org/0000-0002-7791-5511"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruixuan Li","raw_affiliation_strings":["Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3051,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.58741556,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"397","last_page":"398"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":1.0,"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":1.0,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9991000294685364,"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/T12676","display_name":"Machine Learning and ELM","score":0.9984999895095825,"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":0.8006235361099243},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.7036568522453308},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6275883913040161},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5599197149276733},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4790666997432709},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.45734903216362},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4054560959339142},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3521815538406372}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8006235361099243},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.7036568522453308},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6275883913040161},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5599197149276733},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4790666997432709},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.45734903216362},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4054560959339142},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3521815538406372},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3293883.3295718","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3293883.3295718","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2338908902","https://openalex.org/W2489529491","https://openalex.org/W2594172366","https://openalex.org/W2883283076","https://openalex.org/W3103894541","https://openalex.org/W4301361180"],"related_works":["https://openalex.org/W2731899572","https://openalex.org/W3215138031","https://openalex.org/W1604898313","https://openalex.org/W3009238340","https://openalex.org/W2939353110","https://openalex.org/W2164287667","https://openalex.org/W4233815414","https://openalex.org/W2140418760","https://openalex.org/W2126887587","https://openalex.org/W2034384303"],"abstract_inverted_index":{"Ultra-deep":[0],"neural":[1,30],"network(UDNN)":[2],"tends":[3],"to":[4,15,48,58,82,102],"yield":[5],"higher-quality":[6],"model":[7],"but":[8],"its":[9],"training":[10,62,116],"process":[11,63],"is":[12,21,79,100],"often":[13],"difficult":[14],"handle.":[16],"Scarce":[17],"GPU":[18,55,75,135],"DRAM":[19],"capacity":[20],"the":[22,27,33,50,61,84,104,109,113,125],"primary":[23],"bottleneck":[24],"that":[25,46],"limits":[26],"depth":[28],"of":[29,35,53,115,127],"network":[31],"and":[32,76,118,133],"range":[34],"trainable":[36],"minibatch":[37],"size.":[38],"In":[39],"this":[40],"paper,":[41],"we":[42,123],"present":[43],"a":[44,67,92],"scheme":[45,129],"dedicates":[47],"make":[49],"utmost":[51],"use":[52],"finite":[54],"memory":[56,78],"resource":[57],"speed":[59],"up":[60],"for":[64],"UDNN.":[65],"Firstly,":[66],"performance-model":[68],"guided":[69],"dynamic":[70],"swap":[71,110],"out/in":[72],"strategy":[73,111],"between":[74],"host":[77],"carefully":[80],"orchestrated":[81],"tackle":[83],"out-of-memory":[85],"problem":[86],"without":[87],"introducing":[88],"performance":[89],"penalty.":[90],"Then,":[91],"hyperparameter":[93],"(minibatch":[94],"size,":[95],"learning":[96],"rate)":[97],"tuning":[98],"policy":[99],"designed":[101],"explore":[103],"optimal":[105],"configuration":[106],"after":[107],"applying":[108],"from":[112],"perspectives":[114],"time":[117],"final":[119],"accuracy":[120],"simultaneously.":[121],"Finally,":[122],"verify":[124],"effectiveness":[126],"our":[128],"in":[130],"both":[131],"single":[132],"distributed":[134],"mode.":[136]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}