{"id":"https://openalex.org/W4386716292","doi":"https://doi.org/10.54254/2755-2721/6/20230600","title":"Study on pruning optimization based on HRank pruning method","display_name":"Study on pruning optimization based on HRank pruning method","publication_year":2023,"publication_date":"2023-06-14","ids":{"openalex":"https://openalex.org/W4386716292","doi":"https://doi.org/10.54254/2755-2721/6/20230600"},"language":"en","primary_location":{"id":"doi:10.54254/2755-2721/6/20230600","doi":"https://doi.org/10.54254/2755-2721/6/20230600","is_oa":true,"landing_page_url":"https://doi.org/10.54254/2755-2721/6/20230600","pdf_url":null,"source":{"id":"https://openalex.org/S4387281889","display_name":"Applied and Computational Engineering","issn_l":"2755-2721","issn":["2755-2721","2755-273X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied and Computational Engineering","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.54254/2755-2721/6/20230600","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102085299","display_name":"Sheng Lu","orcid":"https://orcid.org/0000-0001-8212-3183","observed_orcids":["https://orcid.org/0000-0001-8212-3183"]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Sheng Lu","raw_affiliation_strings":["Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5102085299"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"6","issue":"1","first_page":"1196","last_page":"1203"},"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/T12535","display_name":"Machine Learning and Data Classification","score":0.0,"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":0.0,"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/convolutional-neural-network-pruning","display_name":"convolutional neural network pruning","score":0.8500000238418579},{"id":"https://openalex.org/keywords/model-compression","display_name":"model compression","score":0.6959999799728394},{"id":"https://openalex.org/keywords/cifar-10","display_name":"CIFAR-10","score":0.9909999966621399},{"id":"https://openalex.org/keywords/parameter-compression","display_name":"parameter compression","score":0.367000013589859},{"id":"https://openalex.org/keywords/flops-reduction","display_name":"FLOPs reduction","score":0.7699999809265137},{"id":"https://openalex.org/keywords/learning-rate-optimization","display_name":"learning rate optimization","score":0.7919999957084656},{"id":"https://openalex.org/keywords/low-power-deployment","display_name":"low-power deployment","score":0.34299999475479126}],"concepts":[{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.8030469417572021},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.7703917026519775},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.6920033097267151},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6738354563713074},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.6189034581184387},{"id":"https://openalex.org/C94835093","wikidata":"https://www.wikidata.org/wiki/Q3113333","display_name":"Data compression ratio","level":5,"score":0.5588285326957703},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.5556641221046448},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.47664675116539},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45255956053733826},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.41775158047676086},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4111621379852295},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37714049220085144},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.275309681892395},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.24324196577072144},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.05519533157348633},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.05328261852264404},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","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:10.54254/2755-2721/6/20230600","doi":"https://doi.org/10.54254/2755-2721/6/20230600","is_oa":true,"landing_page_url":"https://doi.org/10.54254/2755-2721/6/20230600","pdf_url":null,"source":{"id":"https://openalex.org/S4387281889","display_name":"Applied and Computational Engineering","issn_l":"2755-2721","issn":["2755-2721","2755-273X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied and Computational Engineering","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.54254/2755-2721/6/20230600","doi":"https://doi.org/10.54254/2755-2721/6/20230600","is_oa":true,"landing_page_url":"https://doi.org/10.54254/2755-2721/6/20230600","pdf_url":null,"source":{"id":"https://openalex.org/S4387281889","display_name":"Applied and Computational Engineering","issn_l":"2755-2721","issn":["2755-2721","2755-273X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied and Computational Engineering","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2912871542","https://openalex.org/W3034513523","https://openalex.org/W3118608800","https://openalex.org/W3166440012","https://openalex.org/W3202770052","https://openalex.org/W3203553414"],"related_works":["https://openalex.org/W4413839448","https://openalex.org/W4255479302","https://openalex.org/W3034513523","https://openalex.org/W4406754279","https://openalex.org/W2891300275","https://openalex.org/W4403886982","https://openalex.org/W4411122370","https://openalex.org/W7103649284","https://openalex.org/W3119066197","https://openalex.org/W4285188871"],"abstract_inverted_index":{"Convolutional":[0],"neural":[1,32,61,94],"network":[2,95],"(CNN),":[3],"as":[4],"one":[5],"of":[6,11,27,30,57,59,92,100,117,127,156,189,200,216,230,236,248],"the":[7,25,28,55,90,125,145,152,179,186,192,195,198,207,212,217,224,228,233,245,257,262,267],"most":[8],"important":[9,142,161,171],"pillars":[10],"deep":[12],"learning":[13,204,263,268],"technology,":[14],"has":[15],"been":[16],"paid":[17],"increased":[18],"attention":[19],"to":[20,49,69,72,124,239],"by":[21,24],"researchers.":[22],"However,":[23],"expansion":[26],"application":[29],"convolutional":[31,60,93,219],"network,":[33],"it":[34],"faces":[35],"more":[36,38,42,44,53,141,160],"and":[37,41,43,80,138,169,244],"complex":[39],"problems":[40,52],"diverse":[45],"situations.":[46],"In":[47,255],"order":[48],"solve":[50],"these":[51],"appropriately,":[54],"number":[56],"parameters":[58],"networks":[62],"continuously":[63],"increases.":[64],"This":[65],"limits":[66],"its":[67,271],"potential":[68],"be":[70],"deployed":[71],"distal":[73],"devices":[74],"with":[75,97,165,175,185,241,252],"relatively":[76],"low":[77],"computing":[78],"power":[79],"memory":[81],"space.":[82],"To":[83],"improve":[84],"this":[85,87],"situation,":[86],"paper":[88,180,196,208,258],"studies":[89],"compression":[91,154,167,177,183,214],"model":[96],"acceptable":[98,187],"sacrifice":[99],"accuracy.":[101,190],"Based":[102],"on":[103,106],"Pytorch,":[104],"Resnet-56":[105],"CIFAR-10":[107],"is":[108,148,221,265],"pruned.":[109],"By":[110,150],"using":[111],"HRank":[112],"pruning":[113,146,201],"method,":[114],"convolution":[115,119,136,143,158],"kernels":[116,137],"each":[118],"layers":[120],"are":[121,163,173],"ordered":[122],"according":[123],"size":[126],"their":[128],"determinant":[129],"rank.":[130],"Through":[131],"deleting":[132],"low-rank,":[133],"less":[134,170],"importance":[135],"reserving":[139],"high-rank,":[140],"kernels,":[144],"purpose":[147],"achieved.":[149],"changing":[151],"default":[153],"ratio":[155],"different":[157,203],"layer,":[159],"ones":[162,172],"applied":[164,174],"lower":[166],"rates":[168],"higher":[176,182],"rates,":[178],"achieves":[181],"rate":[184,215,235,247,264],"loss":[188],"At":[191],"same":[193],"time,":[194],"tests":[197],"efficiency":[199,269],"under":[202],"rates.":[205],"Finally,":[206],"finds":[209,259],"that":[210,260],"when":[211,261],"preset":[213],"intermediate":[218],"layer":[220],"changed":[222],"slightly,":[223],"accuracy":[225],"maintains":[226],"at":[227],"level":[229],"92.720%":[231],"but":[232],"compress":[234,246],"Params":[237],"reaches":[238,250,270],"44.7%":[240],"0.47M":[242],"left":[243],"Flops":[249],"51.1%":[251],"61.39M":[253],"left.":[254],"addition,":[256],"0.05,":[266],"optimum.":[272]},"counts_by_year":[],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2023-09-14T00:00:00"}