{"id":"https://openalex.org/W3131107792","doi":"https://doi.org/10.1109/tsusc.2021.3060690","title":"AdaPrune: An Accelerator-Aware Pruning Technique for Sustainable CNN Accelerators","display_name":"AdaPrune: An Accelerator-Aware Pruning Technique for Sustainable CNN Accelerators","publication_year":2021,"publication_date":"2021-02-19","ids":{"openalex":"https://openalex.org/W3131107792","doi":"https://doi.org/10.1109/tsusc.2021.3060690","mag":"3131107792"},"language":"en","primary_location":{"id":"doi:10.1109/tsusc.2021.3060690","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsusc.2021.3060690","pdf_url":null,"source":{"id":"https://openalex.org/S4210221417","display_name":"IEEE Transactions on Sustainable Computing","issn_l":"2377-3782","issn":["2377-3782","2377-3790"],"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 Sustainable Computing","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/A5100352041","display_name":"Jiajun Li","orcid":"https://orcid.org/0000-0002-7208-9345"},"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":"Jiajun Li","raw_affiliation_strings":["Department of Electrical and Computer Engineering, George Washington University, Washington, DC, USA"],"raw_orcid":"https://orcid.org/0000-0002-7208-9345","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, George Washington University, Washington, DC, USA","institution_ids":["https://openalex.org/I193531525"]}]},{"author_position":"last","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, George Washington University, Washington, DC, USA","institution_ids":["https://openalex.org/I193531525"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I193531525"],"apc_list":null,"apc_paid":null,"fwci":1.4133,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.8323399,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"7","issue":"1","first_page":"47","last_page":"60"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9898999929428101,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9897000193595886,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.8006675243377686},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7795042991638184},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.758857011795044},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.7463903427124023},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6794003844261169},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.5012149810791016},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.44558489322662354},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.44363173842430115},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.43507862091064453},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4343174397945404},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.43238285183906555},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.42521804571151733},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.36829009652137756},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.36490553617477417},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34406930208206177},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.2938060164451599},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.26820385456085205},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0676717460155487}],"concepts":[{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.8006675243377686},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7795042991638184},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.758857011795044},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.7463903427124023},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6794003844261169},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.5012149810791016},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.44558489322662354},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.44363173842430115},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.43507862091064453},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4343174397945404},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.43238285183906555},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.42521804571151733},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.36829009652137756},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.36490553617477417},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34406930208206177},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.2938060164451599},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26820385456085205},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0676717460155487},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"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/tsusc.2021.3060690","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsusc.2021.3060690","pdf_url":null,"source":{"id":"https://openalex.org/S4210221417","display_name":"IEEE Transactions on Sustainable Computing","issn_l":"2377-3782","issn":["2377-3782","2377-3790"],"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 Sustainable Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.800000011920929}],"awards":[{"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/G5209484801","display_name":null,"funder_award_id":"CCF-1565273","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7203528079","display_name":null,"funder_award_id":"CCF-1702980","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":58,"referenced_works":["https://openalex.org/W1995562189","https://openalex.org/W2094756095","https://openalex.org/W2162639668","https://openalex.org/W2194775991","https://openalex.org/W2276892413","https://openalex.org/W2294282016","https://openalex.org/W2300242332","https://openalex.org/W2466675884","https://openalex.org/W2530876040","https://openalex.org/W2604998962","https://openalex.org/W2605487586","https://openalex.org/W2606722458","https://openalex.org/W2612076670","https://openalex.org/W2618530766","https://openalex.org/W2625457103","https://openalex.org/W2707890836","https://openalex.org/W2736953746","https://openalex.org/W2790925711","https://openalex.org/W2795127895","https://openalex.org/W2798275680","https://openalex.org/W2798317693","https://openalex.org/W2808168148","https://openalex.org/W2896006880","https://openalex.org/W2904295992","https://openalex.org/W2904902077","https://openalex.org/W2906043559","https://openalex.org/W2906374897","https://openalex.org/W2913104037","https://openalex.org/W2932154853","https://openalex.org/W2933438941","https://openalex.org/W2940862705","https://openalex.org/W2950656546","https://openalex.org/W2953190524","https://openalex.org/W2953915593","https://openalex.org/W2962818002","https://openalex.org/W2962851801","https://openalex.org/W2962965870","https://openalex.org/W2963594949","https://openalex.org/W2964350391","https://openalex.org/W2979313476","https://openalex.org/W2979439447","https://openalex.org/W2979719709","https://openalex.org/W2979754840","https://openalex.org/W2979838629","https://openalex.org/W2984035546","https://openalex.org/W4212788319","https://openalex.org/W4240168186","https://openalex.org/W4244330903","https://openalex.org/W4246193833","https://openalex.org/W4247470470","https://openalex.org/W4249932213","https://openalex.org/W4251575795","https://openalex.org/W4375869345","https://openalex.org/W6677580257","https://openalex.org/W6726275242","https://openalex.org/W6739917289","https://openalex.org/W6755034786","https://openalex.org/W6755526309"],"related_works":["https://openalex.org/W2913534066","https://openalex.org/W2970375204","https://openalex.org/W3176282186","https://openalex.org/W2973622361","https://openalex.org/W4387489555","https://openalex.org/W4395024198","https://openalex.org/W4293053895","https://openalex.org/W4288024917","https://openalex.org/W2983364019","https://openalex.org/W2998183476"],"abstract_inverted_index":{"Convolutional":[0],"neural":[1,23],"network":[2,24,159],"(CNN)":[3],"accelerators":[4,104,183],"have":[5],"achieved":[6],"great":[7],"success":[8],"from":[9],"cloud":[10],"to":[11,31,73,105,142,197,206],"edge":[12,38],"scenarios.":[13],"However,":[14],"given":[15],"the":[16,46,102,108,127,139,145,157,166,171],"trend":[17],"towards":[18],"even":[19],"larger":[20],"and":[21,71,77,120,173,201],"deeper":[22],"models,":[25],"it":[26],"remains":[27],"a":[28,63],"challenging":[29],"problem":[30],"efficiently":[32],"process":[33],"these":[34],"CNNs":[35],"especially":[36],"on":[37,179],"devices":[39],"with":[40,184],"limited":[41],"energy":[42,47,78,174,203],"budget.":[43],"Accordingly,":[44],"reducing":[45],"consumption":[48],"is":[49],"of":[50,113,131],"paramount":[51],"importance":[52],"for":[53,80,101,165],"sustainable":[54],"CNN":[55,81,99,133,182],"accelerators.":[56,82],"In":[57,154],"this":[58],"paper,":[59],"we":[60],"propose":[61],"AdaPrune,":[62],"novel":[64],"pruning":[65,85,100,119],"technique":[66],"that":[67,87,144,193],"reduces":[68],"model":[69],"size":[70],"computation":[72],"achieve":[74],"performance":[75,172,199],"improvement":[76],"savings":[79,204],"Unlike":[83],"previous":[84],"techniques":[86,141],"sacrifice":[88],"either":[89],"computational":[90,163],"regularity":[91,164],"or":[92],"accuracy,":[93],"AdaPrune":[94,111,135,178,194],"maintains":[95],"both":[96],"by":[97],"customizing":[98],"underlying":[103,167],"maximally":[106],"leverage":[107],"sparsity":[109],"benefits.":[110],"consists":[112],"two":[114,140],"techniques:":[115],"input":[116],"channel":[117,122],"group":[118,123],"output":[121],"pruning.":[124,208],"By":[125],"analyzing":[126],"weight":[128],"fetching":[129,152],"patterns":[130],"sparse":[132,181],"accelerators,":[134,168],"adaptively":[136],"switches":[137],"between":[138],"guarantee":[143],"zeros":[146],"are":[147],"evenly":[148],"distributed":[149],"in":[150],"each":[151],"group.":[153],"doing":[155],"so,":[156],"pruned":[158],"structure":[160],"preserves":[161],"customized":[162],"thereby":[169],"boosting":[170],"efficiency.":[175],"We":[176],"evaluate":[177],"three":[180],"different":[185],"spatial":[186],"tiling":[187],"strategies.":[188],"The":[189],"experimental":[190],"results":[191],"show":[192],"achieves":[195],"up":[196],"1.6×":[198],"speedup,":[200],"1.5×":[202],"compared":[205],"unstructured":[207]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}