{"id":"https://openalex.org/W4284967031","doi":"https://doi.org/10.1109/tnnls.2022.3186008","title":"Efficient Neural Network Compression Inspired by Compressive Sensing","display_name":"Efficient Neural Network Compression Inspired by Compressive Sensing","publication_year":2022,"publication_date":"2022-07-08","ids":{"openalex":"https://openalex.org/W4284967031","doi":"https://doi.org/10.1109/tnnls.2022.3186008","pmid":"https://pubmed.ncbi.nlm.nih.gov/35802547"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2022.3186008","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2022.3186008","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5050309466","display_name":"Wei Gao","orcid":"https://orcid.org/0000-0001-7429-5495"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Gao","raw_affiliation_strings":["School of Electronic and Computer Engineering, Peking University, Shenzhen, China","Peng Cheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-7429-5495","affiliations":[{"raw_affiliation_string":"School of Electronic and Computer Engineering, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100720831","display_name":"Yang Guo","orcid":"https://orcid.org/0000-0001-5240-657X"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Guo","raw_affiliation_strings":["School of Electronic and Computer Engineering, Peking University, Shenzhen, China","Peng Cheng Laboratory, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Computer Engineering, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039832462","display_name":"Siwei Ma","orcid":"https://orcid.org/0000-0002-2731-5403"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siwei Ma","raw_affiliation_strings":["Institute of Digital Media, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2731-5403","affiliations":[{"raw_affiliation_string":"Institute of Digital Media, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100447691","display_name":"Ge Li","orcid":"https://orcid.org/0000-0003-0140-0949"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ge Li","raw_affiliation_strings":["School of Electronic and Computer Engineering, Peking University, Shenzhen, China","Peng Cheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-0140-0949","affiliations":[{"raw_affiliation_string":"School of Electronic and Computer Engineering, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008386708","display_name":"Sam Kwong","orcid":"https://orcid.org/0000-0001-7484-7261"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Sam Kwong","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, Kowloon Tong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0001-7484-7261","affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Kowloon Tong, Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.6506,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.94074451,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"35","issue":"2","first_page":"1965","last_page":"1979"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11447","display_name":"Blind Source Separation Techniques","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.996399998664856,"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/flops","display_name":"FLOPS","score":0.8342315554618835},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5583845973014832},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5405693054199219},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.509715735912323},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5020132064819336},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.45447027683258057},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.44291532039642334},{"id":"https://openalex.org/keywords/compressed-sensing","display_name":"Compressed sensing","score":0.4240201711654663},{"id":"https://openalex.org/keywords/compression-ratio","display_name":"Compression ratio","score":0.42343685030937195},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.380462646484375},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2846851348876953},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.20303264260292053},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.09034064412117004}],"concepts":[{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.8342315554618835},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5583845973014832},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5405693054199219},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.509715735912323},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5020132064819336},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.45447027683258057},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.44291532039642334},{"id":"https://openalex.org/C124851039","wikidata":"https://www.wikidata.org/wiki/Q2665459","display_name":"Compressed sensing","level":2,"score":0.4240201711654663},{"id":"https://openalex.org/C25797200","wikidata":"https://www.wikidata.org/wiki/Q828137","display_name":"Compression ratio","level":3,"score":0.42343685030937195},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.380462646484375},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2846851348876953},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.20303264260292053},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.09034064412117004},{"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/C511840579","wikidata":"https://www.wikidata.org/wiki/Q12757","display_name":"Internal combustion engine","level":2,"score":0.0},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","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/C171146098","wikidata":"https://www.wikidata.org/wiki/Q124192","display_name":"Automotive engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2022.3186008","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2022.3186008","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:35802547","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35802547","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3740448160","display_name":null,"funder_award_id":"2019A1515012031","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"},{"id":"https://openalex.org/G4397451791","display_name":null,"funder_award_id":"61801303","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5426793764","display_name":null,"funder_award_id":"GXWD20201231165807007-20200806163656003","funder_id":"https://openalex.org/F4320329791","funder_display_name":"Shenzhen Fundamental Research Program"},{"id":"https://openalex.org/G8212228297","display_name":null,"funder_award_id":"62031013","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8862036600","display_name":null,"funder_award_id":"2020AAA0103501","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320329791","display_name":"Shenzhen Fundamental Research Program","ror":null},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":76,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1774526428","https://openalex.org/W1821462560","https://openalex.org/W1903029394","https://openalex.org/W1919191429","https://openalex.org/W1935978687","https://openalex.org/W1988451630","https://openalex.org/W1989060270","https://openalex.org/W1993335267","https://openalex.org/W2000769684","https://openalex.org/W2058641082","https://openalex.org/W2112796928","https://openalex.org/W2117539524","https://openalex.org/W2118718620","https://openalex.org/W2129131372","https://openalex.org/W2129638195","https://openalex.org/W2135046866","https://openalex.org/W2146842127","https://openalex.org/W2151693816","https://openalex.org/W2154590891","https://openalex.org/W2160979406","https://openalex.org/W2194775991","https://openalex.org/W2233116163","https://openalex.org/W2319920447","https://openalex.org/W2608787653","https://openalex.org/W2798405286","https://openalex.org/W2808168148","https://openalex.org/W2896457183","https://openalex.org/W2901505625","https://openalex.org/W2924515500","https://openalex.org/W2963037989","https://openalex.org/W2963125010","https://openalex.org/W2963145730","https://openalex.org/W2963163009","https://openalex.org/W2963382930","https://openalex.org/W2964137095","https://openalex.org/W2964233199","https://openalex.org/W2983108667","https://openalex.org/W2987906097","https://openalex.org/W3034251466","https://openalex.org/W3034408420","https://openalex.org/W3034513523","https://openalex.org/W3034818206","https://openalex.org/W3081131905","https://openalex.org/W3095487519","https://openalex.org/W3101782091","https://openalex.org/W3106153666","https://openalex.org/W3118608800","https://openalex.org/W3136450870","https://openalex.org/W3157993436","https://openalex.org/W3173799170","https://openalex.org/W3185811833","https://openalex.org/W4246853318","https://openalex.org/W4250955649","https://openalex.org/W4297775537","https://openalex.org/W4312258136","https://openalex.org/W6620707391","https://openalex.org/W6631660994","https://openalex.org/W6637373629","https://openalex.org/W6677759377","https://openalex.org/W6682848092","https://openalex.org/W6695314431","https://openalex.org/W6700264148","https://openalex.org/W6713134421","https://openalex.org/W6726275242","https://openalex.org/W6736893582","https://openalex.org/W6737664043","https://openalex.org/W6739917289","https://openalex.org/W6741783443","https://openalex.org/W6745499552","https://openalex.org/W6751097180","https://openalex.org/W6755166560","https://openalex.org/W6755207826","https://openalex.org/W6782052538","https://openalex.org/W6783948878","https://openalex.org/W6787972765"],"related_works":["https://openalex.org/W4315697128","https://openalex.org/W3102845713","https://openalex.org/W2971502891","https://openalex.org/W3205506801","https://openalex.org/W2158224665","https://openalex.org/W1512321724","https://openalex.org/W4231317009","https://openalex.org/W2367696392","https://openalex.org/W4293703255","https://openalex.org/W3145562545"],"abstract_inverted_index":{"Traditional":[0],"neural":[1,150],"network":[2,45,143,151],"compression":[3],"(NNC)":[4],"methods":[5,181],"decrease":[6,194,215],"the":[7,15,24,37,67,76,84,95,110,120,135,148,177],"model":[8,105],"size":[9],"and":[10,42,127,129,134,157,187,197,218],"floating-point":[11],"operations":[12],"(FLOPs)":[13],"in":[14,75,83,94,182,207,228],"manner":[16],"of":[17,39,72,116,184,202,223],"screening":[18],"out":[19],"unimportant":[20],"weight":[21,73,125],"parameters;":[22],"however,":[23],"intrinsic":[25],"sparsity":[26,70],"characteristics":[27],"have":[28],"not":[29],"been":[30],"fully":[31],"exploited.":[32],"In":[33],"this":[34],"article,":[35],"from":[36],"perspective":[38],"signal":[40],"processing":[41],"analysis":[43],"for":[44,58,92],"parameters,":[46],"we":[47,100,146,193,214],"propose":[48],"to":[49,88,141,165],"use":[50],"a":[51,102,158,199,220],"compressive":[52],"sensing":[53],"(CS)-based":[54],"method,":[55],"namely":[56],"NNCS,":[57],"performance":[59],"improvements.":[60],"Our":[61],"proposed":[62,111],"NNCS":[63,173],"is":[64],"inspired":[65],"by":[66],"discovery":[68],"that":[69,172],"levels":[71],"parameters":[74,93,126,196,217],"transform":[77,96,139,147],"domain":[78,97],"are":[79],"greater":[80],"than":[81],"those":[82],"original":[85],"domain.":[86],"First,":[87],"achieve":[89,198,219],"sparse":[90,132],"representations":[91,133],"during":[98],"training,":[99],"incorporate":[101],"constrained":[103],"CS":[104],"into":[106,152],"loss":[107],"function.":[108],"Second,":[109],"effective":[112],"training":[113],"process":[114],"consists":[115],"two":[117],"steps,":[118],"where":[119],"first":[121],"step":[122,137],"trains":[123,138],"raw":[124],"induces":[128],"reconstructs":[130],"their":[131],"second":[136],"coefficients":[140],"improve":[142],"performances.":[144],"Finally,":[145],"entire":[149],"another":[153],"new":[154],"domain-based":[155],"representation,":[156],"sparser":[159],"parameter":[160,185],"distribution":[161],"can":[162,174],"be":[163],"obtained":[164],"facilitate":[166],"inference":[167],"acceleration.":[168],"Experimental":[169],"results":[170],"demonstrate":[171],"significantly":[175],"outperform":[176],"other":[178],"existing":[179],"state-of-the-art":[180],"terms":[183],"reductions":[186],"FLOPs.":[188],"With":[189,210],"VGGNet":[190],"on":[191,212],"CIFAR-10,":[192],"94.8%":[195],"76.8%":[200],"reduction":[201,222],"FLOPs,":[203,224],"with":[204,225],"0.13%":[205],"drop":[206,227],"Top-1":[208,229],"accuracy.":[209,230],"ResNet-50":[211],"ImageNet,":[213],"75.6%":[216],"78.9%":[221],"1.24%":[226]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}