{"id":"https://openalex.org/W3089835766","doi":"https://doi.org/10.1109/ijcnn48605.2020.9207531","title":"Hierarchical Group Sparse Regularization for Deep Convolutional Neural Networks","display_name":"Hierarchical Group Sparse Regularization for Deep Convolutional Neural Networks","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3089835766","doi":"https://doi.org/10.1109/ijcnn48605.2020.9207531","mag":"3089835766"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn48605.2020.9207531","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9207531","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","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/A5046417869","display_name":"Kakeru Mitsuno","orcid":null},"institutions":[{"id":"https://openalex.org/I113306721","display_name":"Hiroshima University","ror":"https://ror.org/03t78wx29","country_code":"JP","type":"education","lineage":["https://openalex.org/I113306721"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Kakeru Mitsuno","raw_affiliation_strings":["School of Engineering, Hiroshima University, Higashi Hiroshima, Japan"],"affiliations":[{"raw_affiliation_string":"School of Engineering, Hiroshima University, Higashi Hiroshima, Japan","institution_ids":["https://openalex.org/I113306721"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030040541","display_name":"Junichi Miyao","orcid":"https://orcid.org/0000-0001-8545-0630"},"institutions":[{"id":"https://openalex.org/I113306721","display_name":"Hiroshima University","ror":"https://ror.org/03t78wx29","country_code":"JP","type":"education","lineage":["https://openalex.org/I113306721"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Junichi Miyao","raw_affiliation_strings":["Department of Information Engineering, Hiroshima University, Higashi Hiroshima, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Information Engineering, Hiroshima University, Higashi Hiroshima, Japan","institution_ids":["https://openalex.org/I113306721"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086456461","display_name":"Takio Kurita","orcid":"https://orcid.org/0000-0003-3982-6750"},"institutions":[{"id":"https://openalex.org/I113306721","display_name":"Hiroshima University","ror":"https://ror.org/03t78wx29","country_code":"JP","type":"education","lineage":["https://openalex.org/I113306721"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takio Kurita","raw_affiliation_strings":["Department of Information Engineering, Hiroshima University, Higashi Hiroshima, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Information Engineering, Hiroshima University, Higashi Hiroshima, Japan","institution_ids":["https://openalex.org/I113306721"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5046417869"],"corresponding_institution_ids":["https://openalex.org/I113306721"],"apc_list":null,"apc_paid":null,"fwci":1.617,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.81408556,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T12676","display_name":"Machine Learning and ELM","score":0.9994999766349792,"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/T10057","display_name":"Face and Expression Recognition","score":0.9991999864578247,"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/overfitting","display_name":"Overfitting","score":0.7128188014030457},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.6915774941444397},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6211047172546387},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.596286416053772},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5165185332298279},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48215195536613464},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.46284669637680054},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.4286878705024719},{"id":"https://openalex.org/keywords/group","display_name":"Group (periodic table)","score":0.41433268785476685},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.41192197799682617},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.380709707736969}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.7128188014030457},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.6915774941444397},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6211047172546387},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.596286416053772},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5165185332298279},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48215195536613464},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.46284669637680054},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.4286878705024719},{"id":"https://openalex.org/C2781311116","wikidata":"https://www.wikidata.org/wiki/Q83306","display_name":"Group (periodic table)","level":2,"score":0.41433268785476685},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.41192197799682617},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.380709707736969},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn48605.2020.9207531","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9207531","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","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":32,"referenced_works":["https://openalex.org/W1497745584","https://openalex.org/W1686810756","https://openalex.org/W1987371344","https://openalex.org/W2016782026","https://openalex.org/W2037964547","https://openalex.org/W2041891835","https://openalex.org/W2056201402","https://openalex.org/W2088350412","https://openalex.org/W2113328646","https://openalex.org/W2122825543","https://openalex.org/W2135046866","https://openalex.org/W2138019504","https://openalex.org/W2144567071","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2460144244","https://openalex.org/W2554931888","https://openalex.org/W2741485222","https://openalex.org/W2811153427","https://openalex.org/W2907965772","https://openalex.org/W2947963429","https://openalex.org/W2963000224","https://openalex.org/W2970738028","https://openalex.org/W4302613003","https://openalex.org/W6629935912","https://openalex.org/W6637373629","https://openalex.org/W6676664377","https://openalex.org/W6681129735","https://openalex.org/W6684191040","https://openalex.org/W6725543821","https://openalex.org/W6730382033","https://openalex.org/W6741783443"],"related_works":["https://openalex.org/W4362597605","https://openalex.org/W1574414179","https://openalex.org/W4297676672","https://openalex.org/W3099765033","https://openalex.org/W4226493464","https://openalex.org/W4312417841","https://openalex.org/W3133861977","https://openalex.org/W2951211570","https://openalex.org/W2964954556","https://openalex.org/W3103566983"],"abstract_inverted_index":{"In":[0,65,119,206],"a":[1,24,66,92,101,104,113,162,168,182],"deep":[2],"neural":[3,68],"network":[4,50,69,197,227],"(DNN),":[5],"the":[6,9,49,82,97,117,124,146,153,156,159,171,176,187,193,196,199,207,211,214],"number":[7,200],"of":[8,26,81,126,179,195,201,213],"parameters":[10,41],"is":[11,37,109],"usually":[12],"huge":[13],"to":[14,61,77,100,129,174],"get":[15],"high":[16,204],"learning":[17],"performances.":[18],"For":[19],"that":[20,39],"reason,":[21],"it":[22],"costs":[23],"lot":[25],"memory":[27],"and":[28,32,44,133,164,198],"substantial":[29],"computational":[30],"resources,":[31],"also":[33],"causes":[34],"overfitting.":[35],"It":[36],"known":[38],"some":[40],"are":[42,74],"redundant":[43],"can":[45,151,185],"be":[46],"removed":[47],"from":[48],"without":[51],"decreasing":[52],"performance.":[53,205],"Many":[54],"sparse":[55,72,94,139,149,216],"regularization":[56,95,140,150],"criteria":[57,141],"have":[58],"been":[59],"proposed":[60,145,215],"solve":[62,130],"this":[63,120,131],"problem.":[64],"convolutional":[67,165],"(CNN),":[70],"group":[71,93,115,138,148,163,169,173],"regularizations":[73,217],"often":[75],"used":[76],"remove":[78],"unnecessary":[79,177],"subsets":[80,178],"weights,":[83],"such":[84],"as":[85,103,112,161,167],"filters":[86],"or":[87,158],"channels.":[88],"When":[89],"we":[90,122,134,184,209],"apply":[91],"for":[96,142,155],"weights":[98,188],"connected":[99],"neuron":[102],"group,":[105],"each":[106],"convolution":[107],"filter":[108,166],"not":[110],"treated":[111],"target":[114],"in":[116,170],"regularization.":[118],"paper,":[121],"introduce":[123],"concept":[125],"hierarchical":[127,137,147],"grouping":[128],"problem,":[132],"propose":[135],"several":[136,226],"CNNs.":[143],"Our":[144],"treat":[152],"weight":[154],"input-neuron":[157],"output-neuron":[160],"same":[172],"prune":[175,186],"weights.":[180],"As":[181],"result,":[183],"more":[189],"adequately":[190],"depending":[191],"on":[192,222],"structure":[194],"channels":[202],"keeping":[203],"experiment,":[208],"investigate":[210],"effectiveness":[212],"through":[218],"intensive":[219],"comparison":[220],"experiments":[221],"public":[223],"datasets":[224],"with":[225],"architectures.":[228]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}