{"id":"https://openalex.org/W4401041682","doi":"https://doi.org/10.1109/tcsi.2024.3430831","title":"A Balanced Sparse Matrix Convolution Accelerator for Efficient CNN Training","display_name":"A Balanced Sparse Matrix Convolution Accelerator for Efficient CNN Training","publication_year":2024,"publication_date":"2024-07-26","ids":{"openalex":"https://openalex.org/W4401041682","doi":"https://doi.org/10.1109/tcsi.2024.3430831"},"language":"en","primary_location":{"id":"doi:10.1109/tcsi.2024.3430831","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsi.2024.3430831","pdf_url":null,"source":{"id":"https://openalex.org/S116977442","display_name":"IEEE Transactions on Circuits and Systems I Regular Papers","issn_l":"1549-8328","issn":["1549-8328","1558-0806"],"is_oa":false,"is_in_doaj":false,"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 Transactions on Circuits and Systems I: Regular Papers","raw_type":"journal-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/A5063521542","display_name":"Yuechen Chen","orcid":"https://orcid.org/0000-0001-6671-8443"},"institutions":[{"id":"https://openalex.org/I152830075","display_name":"Frostburg State University","ror":"https://ror.org/048drzm61","country_code":"US","type":"education","lineage":["https://openalex.org/I152830075"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yuechen Chen","raw_affiliation_strings":["Department of Computer Science and Information Technologies, Frostburg State University, Frostburg, MD, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Technologies, Frostburg State University, Frostburg, MD, USA","institution_ids":["https://openalex.org/I152830075"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034189643","display_name":"Ahmed Louri","orcid":"https://orcid.org/0000-0003-4262-6688"},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ahmed Louri","raw_affiliation_strings":["Department of Electrical and Computer Engineering, George Washington University, Washington, DC, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, George Washington University, Washington, DC, USA","institution_ids":["https://openalex.org/I193531525"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100417119","display_name":"Shanshan Liu","orcid":"https://orcid.org/0000-0001-6226-2880"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shanshan Liu","raw_affiliation_strings":["School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001979328","display_name":"Fabrizio Lombardi","orcid":"https://orcid.org/0000-0003-3152-3245"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fabrizio Lombardi","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Northeastern University, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Northeastern University, Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5063521542"],"corresponding_institution_ids":["https://openalex.org/I152830075"],"apc_list":null,"apc_paid":null,"fwci":0.5263,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.64462769,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"71","issue":"10","first_page":"4638","last_page":"4651"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9988999962806702,"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/T13114","display_name":"Image Processing Techniques and Applications","score":0.9957000017166138,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.6811232566833496},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.6365269422531128},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6150137782096863},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.5055923461914062},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.45318812131881714},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3579159379005432},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3500596284866333},{"id":"https://openalex.org/keywords/electronic-engineering","display_name":"Electronic engineering","score":0.34944623708724976},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3420311212539673},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3297423720359802},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1552869975566864},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.15167272090911865},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14283201098442078},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.11421898007392883}],"concepts":[{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.6811232566833496},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.6365269422531128},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6150137782096863},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.5055923461914062},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.45318812131881714},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3579159379005432},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3500596284866333},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.34944623708724976},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3420311212539673},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3297423720359802},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1552869975566864},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.15167272090911865},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14283201098442078},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.11421898007392883},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsi.2024.3430831","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsi.2024.3430831","pdf_url":null,"source":{"id":"https://openalex.org/S116977442","display_name":"IEEE Transactions on Circuits and Systems I Regular Papers","issn_l":"1549-8328","issn":["1549-8328","1558-0806"],"is_oa":false,"is_in_doaj":false,"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 Transactions on Circuits and Systems I: Regular Papers","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1299065893","display_name":null,"funder_award_id":"CCF-1953961","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G1445834140","display_name":null,"funder_award_id":"CCF-1901165","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G1474782865","display_name":null,"funder_award_id":"CCF-2311543","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2232389958","display_name":null,"funder_award_id":"CCF-1812467","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3722230770","display_name":null,"funder_award_id":"CCF-1953980","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7414498835","display_name":null,"funder_award_id":"CCF-2324644","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8709104645","display_name":null,"funder_award_id":"CCF-1812495","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G969502342","display_name":null,"funder_award_id":"CCF-2131946","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2095705004","https://openalex.org/W2108598243","https://openalex.org/W2119144962","https://openalex.org/W2625457103","https://openalex.org/W2919115771","https://openalex.org/W3016542674","https://openalex.org/W3040646053","https://openalex.org/W3092357178","https://openalex.org/W3102175148","https://openalex.org/W3116381138","https://openalex.org/W3134055916","https://openalex.org/W3214870808","https://openalex.org/W4205806473","https://openalex.org/W4281708367","https://openalex.org/W4285117917","https://openalex.org/W4287363917","https://openalex.org/W6674330103","https://openalex.org/W6677580257","https://openalex.org/W6772013979","https://openalex.org/W6790503700"],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W3216976533","https://openalex.org/W3202552726","https://openalex.org/W2279642117","https://openalex.org/W4321636545","https://openalex.org/W2023476765"],"abstract_inverted_index":{"Sparse":[0],"Convolutional":[1],"Neural":[2],"Network":[3],"(CNN)":[4],"training":[5,84,226],"is":[6,56,145,177,192],"well":[7],"known":[8],"to":[9,13,31,41,45,89,180,194,223],"be":[10],"time-consuming":[11],"due":[12],"significant":[14],"off-chip":[15],"memory":[16,33,163],"traffic.":[17],"To":[18,122],"effectively":[19],"deploy":[20],"sparse":[21,83,130,153,225],"training,":[22],"existing":[23,224],"accelerators":[24,38],"store":[25],"matrices":[26,44,64,80,112],"in":[27,62,74,110,114],"a":[28,96,128,140,158,172],"compressed":[29,43],"format":[30],"eliminate":[32],"accesses":[34],"for":[35,100,135,161],"zeros;":[36],"hence,":[37],"are":[39],"designed":[40,179],"process":[42],"avoid":[46],"zero":[47],"computations.":[48],"We":[49],"have":[50],"observed":[51],"that":[52,147,204],"the":[53,60,63,69,82,101,105,111,183,196,205,209,215],"compression":[54,93,98,143,155,170],"rate":[55],"greatly":[57],"affected":[58],"by":[59,212,218],"sparsity":[61,73],"with":[65,157],"different":[66],"formats.":[67],"Given":[68],"varying":[70],"levels":[71],"of":[72,104],"activations,":[75],"weights,":[76],"errors,":[77],"and":[78,186,214],"gradients":[79],"throughout":[81],"process,":[85],"it":[86],"becomes":[87],"impractical":[88],"achieve":[90],"consistently":[91],"high":[92],"rates":[94],"using":[95],"singular":[97],"method":[99],"entire":[102],"duration":[103],"training.":[106,138,166],"Moreover,":[107],"random":[108],"zeros":[109],"result":[113],"irregular":[115],"computation":[116],"patterns,":[117],"further":[118,181],"increasing":[119],"execution":[120,184,210],"time.":[121],"address":[123],"these":[124],"issues,":[125],"we":[126],"propose":[127],"balanced":[129],"matrix":[131,142,154],"convolution":[132],"accelerator":[133,191,207],"design":[134],"efficient":[136],"CNN":[137],"Specifically,":[139],"dual":[141],"technique":[144,176],"developed":[146],"seamlessly":[148],"combines":[149],"two":[150],"widely":[151],"used":[152],"formats":[156],"control":[159],"algorithm":[160],"lower":[162],"traffic":[164],"during":[165],"Based":[167],"on":[168,220],"this":[169],"technique,":[171],"two-level":[173],"workload":[174],"balancing":[175],"then":[178],"reduce":[182],"time":[185,211],"energy":[187,216],"consumption.":[188],"Finally,":[189],"an":[190],"implemented":[193],"support":[195],"proposed":[197,206],"techniques.":[198],"The":[199],"cycle-accurate":[200],"simulation":[201],"results":[202],"show":[203],"reduces":[208],"34%":[213],"consumption":[217],"24%":[219],"average":[221],"compared":[222],"accelerators.":[227]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}