{"id":"https://openalex.org/W2674368400","doi":"https://doi.org/10.1145/3089801.3089806","title":"Pruning Filters and Classes","display_name":"Pruning Filters and Classes","publication_year":2017,"publication_date":"2017-06-19","ids":{"openalex":"https://openalex.org/W2674368400","doi":"https://doi.org/10.1145/3089801.3089806","mag":"2674368400"},"language":"en","primary_location":{"id":"doi:10.1145/3089801.3089806","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3089801.3089806","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3089806&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st International Workshop on Deep Learning for Mobile Systems and Applications","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dl.acm.org/ft_gateway.cfm?id=3089806&type=pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028623085","display_name":"Jia Guo","orcid":"https://orcid.org/0000-0002-0709-261X"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jia Guo","raw_affiliation_strings":["University of California, Los Angeles, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Los Angeles, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082847985","display_name":"Miodrag Potkonjak","orcid":null},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Miodrag Potkonjak","raw_affiliation_strings":["University of California, Los Angeles, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Los Angeles, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I161318765"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1969,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":{"value":0.89338841,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"13","last_page":"17"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.9970999956130981,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9961000084877014,"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/computer-science","display_name":"Computer science","score":0.8106969594955444},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5934988260269165},{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.5894918441772461},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.5864874720573425},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5683561563491821},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.567605197429657},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5346319675445557},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.4317692518234253},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42277202010154724}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8106969594955444},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5934988260269165},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.5894918441772461},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.5864874720573425},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5683561563491821},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.567605197429657},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5346319675445557},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4317692518234253},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42277202010154724},{"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/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3089801.3089806","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3089801.3089806","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3089806&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st International Workshop on Deep Learning for Mobile Systems and Applications","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3089801.3089806","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3089801.3089806","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3089806&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st International Workshop on Deep Learning for Mobile Systems and Applications","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.9100000262260437,"id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G5749020365","display_name":null,"funder_award_id":"1059435","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2674368400.pdf","grobid_xml":"https://content.openalex.org/works/W2674368400.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W1996901117","https://openalex.org/W2114766824","https://openalex.org/W2121775913","https://openalex.org/W2123469553","https://openalex.org/W2125389748","https://openalex.org/W2167215970","https://openalex.org/W2271840356","https://openalex.org/W2285660444","https://openalex.org/W2297325673","https://openalex.org/W2468875367","https://openalex.org/W2515385951","https://openalex.org/W2546536770","https://openalex.org/W2950656546","https://openalex.org/W2963674932","https://openalex.org/W2963911037"],"related_works":["https://openalex.org/W2109940557","https://openalex.org/W2466832359","https://openalex.org/W4391210591","https://openalex.org/W1582019636","https://openalex.org/W1499005795","https://openalex.org/W3172493050","https://openalex.org/W4385420271","https://openalex.org/W4312192618","https://openalex.org/W2593798266","https://openalex.org/W4385414918"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"we":[3,114],"have":[4,97],"witnessed":[5],"more":[6,8,50,172],"and":[7,129],"mobile":[9],"applications":[10,22],"based":[11],"on":[12,106,137],"deep":[13],"learning.":[14],"Widely":[15],"used":[16],"as":[17],"they":[18],"may":[19],"be,":[20],"those":[21],"provide":[23],"little":[24,147],"flexibility":[25],"to":[26,28,52,68,110],"cater":[27],"the":[29,55,70,102,142,151,162],"diversified":[30],"needs":[31],"of":[32,35,166],"different":[33],"groups":[34],"users.":[36],"For":[37],"users":[38,67],"facing":[39],"a":[40,62,111,117,123,130,157,167],"classification":[41,159],"problem,":[42],"it":[43],"is":[44],"natural":[45],"that":[46,65,99,171],"some":[47],"classes":[48,72],"are":[49,57],"important":[51],"them,":[53],"while":[54,141],"rest":[56],"not.":[58],"We":[59],"thus":[60],"propose":[61],"lightweight":[63],"method":[64],"allows":[66],"prune":[69],"unneeded":[71],"together":[73],"with":[74,145],"associated":[75],"filters":[76],"from":[77],"convolutional":[78],"neural":[79],"networks":[80],"(CNNs).":[81],"Such":[82],"customization":[83],"can":[84,115,154],"result":[85],"in":[86,89,120,126,133],"substantial":[87],"reduction":[88],"computational":[90],"costs":[91],"at":[92],"test":[93],"time.":[94],"Early":[95],"results":[96],"shown":[98],"after":[100],"pruning":[101],"Network-in-Network":[103],"(NIN)":[104],"model":[105,153],"CIFAR-10":[107],"dataset\\cite{lim2013network}":[108],"down":[109],"5-class":[112],"classifier,":[113],"trade":[116],"3\\%":[118],"loss":[119],"accuracy":[121,160],"for":[122],"1.63$\\times$":[124],"gain":[125],"energy":[127],"consumption":[128],"1.24$\\times$":[131],"improvement":[132],"latency":[134],"when":[135],"experimenting":[136],"an":[138],"off-the-shelf":[139],"smartphone,":[140],"procedure":[143],"incurs":[144],"very":[146],"overhead.":[148],"After":[149],"pruning,":[150],"custom-tailored":[152],"still":[155],"achieve":[156],"higher":[158],"than":[161],"unmodified":[163],"classifier":[164],"because":[165],"smaller":[168],"problem":[169],"space":[170],"accurately":[173],"reflects":[174],"users'":[175],"needs.":[176]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}