{"id":"https://openalex.org/W2990007648","doi":"https://doi.org/10.1109/hpec.2019.8916506","title":"Performance of Training Sparse Deep Neural Networks on GPUs","display_name":"Performance of Training Sparse Deep Neural Networks on GPUs","publication_year":2019,"publication_date":"2019-09-01","ids":{"openalex":"https://openalex.org/W2990007648","doi":"https://doi.org/10.1109/hpec.2019.8916506","mag":"2990007648"},"language":"en","primary_location":{"id":"doi:10.1109/hpec.2019.8916506","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec.2019.8916506","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE High Performance Extreme Computing Conference (HPEC)","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/A5074472751","display_name":"Jianzong Wang","orcid":"https://orcid.org/0000-0002-9237-4231"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":[],"is_corresponding":true,"raw_author_name":"Jianzong Wang","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd"],"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034232964","display_name":"Zhangcheng Huang","orcid":"https://orcid.org/0000-0001-6563-7668"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Zhangcheng Huang","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd"],"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109480959","display_name":"Lingwei Kong","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Lingwei Kong","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd"],"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016038454","display_name":"Jing Xiao","orcid":"https://orcid.org/0000-0001-9615-4749"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Jing Xiao","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd"],"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100317564","display_name":"Pengyu Wang","orcid":"https://orcid.org/0000-0002-3704-1530"},"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":"Pengyu Wang","raw_affiliation_strings":["Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100388588","display_name":"Lu Zhang","orcid":"https://orcid.org/0000-0001-9567-155X"},"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":"Lu Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100323157","display_name":"Chao Li","orcid":"https://orcid.org/0000-0002-0734-0011"},"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":"Chao Li","raw_affiliation_strings":["Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5074472751"],"corresponding_institution_ids":["https://openalex.org/I4401726822"],"apc_list":null,"apc_paid":null,"fwci":1.1201,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.84217434,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":97},"biblio":{"volume":"abs 1905 416","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12676","display_name":"Machine Learning and ELM","score":0.9970999956130981,"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/T12676","display_name":"Machine Learning and ELM","score":0.9970999956130981,"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":0.9896000027656555,"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/T12326","display_name":"Network Packet Processing and Optimization","score":0.9871000051498413,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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":0.8224236369132996},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.7003343105316162},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6299962401390076},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.577005922794342},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5448105931282043},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.48020467162132263},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4411258399486542},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43166327476501465},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.4008183181285858},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39254921674728394},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.16170421242713928}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8224236369132996},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.7003343105316162},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6299962401390076},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.577005922794342},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5448105931282043},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.48020467162132263},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4411258399486542},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43166327476501465},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.4008183181285858},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39254921674728394},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.16170421242713928},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpec.2019.8916506","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec.2019.8916506","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE High Performance Extreme Computing Conference (HPEC)","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":25,"referenced_works":["https://openalex.org/W316935178","https://openalex.org/W1965034778","https://openalex.org/W1965248225","https://openalex.org/W1989337816","https://openalex.org/W2015103469","https://openalex.org/W2088866486","https://openalex.org/W2104636679","https://openalex.org/W2124807415","https://openalex.org/W2141003547","https://openalex.org/W2158899491","https://openalex.org/W2162283062","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2257979135","https://openalex.org/W2271304962","https://openalex.org/W2902093742","https://openalex.org/W2952230511","https://openalex.org/W2963674932","https://openalex.org/W3100809954","https://openalex.org/W3100839241","https://openalex.org/W4247712932","https://openalex.org/W6647080550","https://openalex.org/W6683738474","https://openalex.org/W6684191040","https://openalex.org/W6910447991"],"related_works":["https://openalex.org/W2770234245","https://openalex.org/W4377865163","https://openalex.org/W3193857078","https://openalex.org/W2888956734","https://openalex.org/W3000197790","https://openalex.org/W4315865067","https://openalex.org/W2979433843","https://openalex.org/W3208304128","https://openalex.org/W4390846322","https://openalex.org/W4285818394"],"abstract_inverted_index":{"Deep":[0],"neural":[1,22,69,76],"networks":[2,23],"have":[3,44,81],"revolutionized":[4],"the":[5,13,28,39,46,60,64,67,83,93,109,119,152,158,183,190,194,204],"field":[6],"of":[7,20,30,48,121,154,160,189,214],"machine":[8],"learning":[9],"by":[10,56],"dramatically":[11],"improving":[12],"state-of-the-art":[14],"in":[15,124],"various":[16],"domains.":[17],"The":[18],"sizes":[19],"deep":[21],"(DNNs)":[24],"are":[25,210],"rapidly":[26],"outgrowing":[27],"capacity":[29],"hardware":[31],"to":[32,92,150,173,181],"fast":[33],"store":[34],"and":[35,53,102,135,156,193,201],"train":[36,91],"them.":[37],"Over":[38],"past":[40],"few":[41],"decades,":[42],"researches":[43],"explored":[45],"prospect":[47],"sparse":[49,75,88,171],"DNNs":[50,89,98,123,127,155,184],"before,":[51],"during,":[52],"after":[54],"training":[55,159,191],"pruning":[57],"edges":[58],"from":[59,169],"underlying":[61],"topology.":[62],"After":[63],"above":[65],"operation,":[66],"generated":[68],"network":[70],"is":[71],"known":[72],"as":[73,96],"a":[74,132,143,166,179],"network.":[77],"More":[78],"recent":[79],"works":[80],"demonstrated":[82],"remarkable":[84],"results":[85,188],"that":[86,111,198],"certain":[87],"can":[90,128],"same":[94],"precision":[95],"dense":[97],"at":[99,131],"lower":[100,136],"runtime":[101],"storage":[103],"cost.":[104,137],"Although":[105],"existing":[106],"methods":[107],"ease":[108],"situation":[110],"high":[112],"demand":[113],"for":[114],"computation":[115,175],"resources":[116],"severely":[117],"hinders":[118],"deployment":[120],"large-scale":[122],"resource-constrained":[125],"devices,":[126],"be":[129],"trained":[130],"faster":[133],"speed":[134],"In":[138],"this":[139],"work,":[140],"we":[141],"propose":[142],"Fine-tune":[144],"Structured":[145],"Sparsity":[146],"Learning":[147],"(FSSL)":[148],"method":[149],"regularize":[151],"structures":[153],"accelerate":[157,182],"DNNs.":[161],"FSSL":[162],"can:":[163],"(1)":[164],"learn":[165],"compact":[167],"structure":[168],"large":[170],"DNN":[172],"reduce":[174],"cost;":[176],"(2)":[177],"obtain":[178],"hardware-friendly":[180],"evaluation":[185],"efficiently.":[186],"Experimental":[187],"time":[192],"compression":[195],"rate":[196],"show":[197],"superior":[199],"performance":[200],"efficiency":[202],"than":[203],"Matlab":[205],"example":[206],"code.":[207],"These":[208],"speedups":[209,213],"about":[211],"twice":[212],"non-structured":[215],"sparsity.":[216]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}