{"id":"https://openalex.org/W2940478336","doi":null,"title":"LeGR: Filter Pruning via Learned Global Ranking.","display_name":"LeGR: Filter Pruning via Learned Global Ranking.","publication_year":2019,"publication_date":"2019-04-28","ids":{"openalex":"https://openalex.org/W2940478336","mag":"2940478336"},"language":"en","primary_location":{"id":"mag:2940478336","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/1904.12368v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/abs/1904.12368v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013507891","display_name":"Ting-Wu Chin","orcid":"https://orcid.org/0000-0003-2953-0489","observed_orcids":["https://orcid.org/0000-0003-2953-0489"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ting-Wu Chin","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-2953-0489","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101602646","display_name":"Ruizhou Ding","orcid":"https://orcid.org/0000-0002-6357-6723","observed_orcids":["https://orcid.org/0000-0002-6357-6723","https://orcid.org/0000-0003-4311-3761"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruizhou Ding","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-4311-3761","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103551927","display_name":"Cha Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cha Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5065985595","display_name":"Diana Marculescu","orcid":"https://orcid.org/0000-0002-5734-4221","observed_orcids":["https://orcid.org/0000-0002-5734-4221"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Diana Marculescu","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-5734-4221","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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/filter-pruning","display_name":"filter pruning","score":0.968999981880188},{"id":"https://openalex.org/keywords/convolutional-neural-network-compression","display_name":"convolutional neural network compression","score":0.8109999895095825},{"id":"https://openalex.org/keywords/accuracy-latency-trade-off","display_name":"accuracy-latency trade-off","score":0.9010000228881836},{"id":"https://openalex.org/keywords/model-complexity","display_name":"model complexity","score":0.3190000057220459},{"id":"https://openalex.org/keywords/resnet","display_name":"ResNet","score":0.4909999966621399},{"id":"https://openalex.org/keywords/mobilenetv2","display_name":"MobileNetV2","score":0.9819999933242798},{"id":"https://openalex.org/keywords/embodied-ai","display_name":"embodied AI","score":0.43799999356269836}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8091586232185364},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.7594306468963623},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.5636467933654785},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5318614840507507},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5207362174987793},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5115078687667847},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45965853333473206},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4260771870613098},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4254756271839142},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.4250991642475128},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.13890138268470764},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.09042492508888245},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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":"mag:2940478336","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/1904.12368v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:2940478336","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/1904.12368v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1797268635","https://openalex.org/W2117539524","https://openalex.org/W2619096655","https://openalex.org/W2619890685","https://openalex.org/W2757143157","https://openalex.org/W2770882886","https://openalex.org/W2786054724","https://openalex.org/W2810271953","https://openalex.org/W2902251695","https://openalex.org/W2963094099","https://openalex.org/W2963145730","https://openalex.org/W2963363373","https://openalex.org/W2963382930","https://openalex.org/W2963398264","https://openalex.org/W2964217527","https://openalex.org/W2964233199","https://openalex.org/W3118608800"],"related_works":["https://openalex.org/W3011514561","https://openalex.org/W3108350280","https://openalex.org/W4399924917","https://openalex.org/W4296440277","https://openalex.org/W4313415362","https://openalex.org/W2970632972","https://openalex.org/W4285059684","https://openalex.org/W4389408880","https://openalex.org/W3005963186","https://openalex.org/W2893585013"],"abstract_inverted_index":{"Pruning":[0],"convolutional":[1],"filters":[2,167],"has":[3],"demonstrated":[4],"its":[5,243],"effectiveness":[6],"in":[7,12,107],"compressing":[8],"ConvNets.":[9],"Prior":[10],"art":[11],"filter":[13,100],"pruning":[14,190],"requires":[15],"users":[16],"to":[17,81,104,133,160,177,200,203,241],"specify":[18],"a":[19,35,89,92,108,117,135,162,179],"target":[20,36],"model":[21,24,37,131],"complexity":[22,38],"(e.g.,":[23],"size":[25],"or":[26,212],"FLOP":[27],"count)":[28],"for":[29,42],"the":[30,58,61,67,70,73,76,95,128,166,172,191,225],"resulting":[31],"architecture.":[32],"However,":[33],"determining":[34],"can":[39,65,78,111],"be":[40,79,105,112,201],"difficult":[41],"optimizing":[43],"various":[44,140],"embodied":[45],"AI":[46],"applications":[47],"such":[48],"as":[49],"autonomous":[50],"robots,":[51],"drones,":[52],"and":[53,60,97,142,235,239],"user-facing":[54],"applications.":[55],"First,":[56],"both":[57],"accuracy":[59,96,141],"speed":[62,98],"of":[63,69,75,130,137,146,165,171,181],"ConvNets":[64,85,138],"affect":[66],"performance":[68,74,214],"application.":[71],"Second,":[72],"application":[77],"hard":[80],"assess":[82],"without":[83],"evaluating":[84],"during":[86],"inference.":[87],"As":[88],"consequence,":[90],"finding":[91],"sweet-spot":[93],"between":[94],"via":[99],"pruning,":[101],"which":[102,174],"needs":[103],"done":[106],"trial-and-error":[109],"fashion,":[110],"time-consuming.":[113],"This":[114],"work":[115,208],"takes":[116],"first":[118],"step":[119],"toward":[120],"making":[121],"this":[122,156,248],"process":[123],"more":[124],"efficient":[125],"by":[126,189],"altering":[127],"goal":[129],"compression":[132],"producing":[134,147],"set":[136,180],"with":[139,220,237],"latency":[143,153],"trade-offs":[144,188],"instead":[145],"one":[148],"ConvNet":[149,182],"targeting":[150,216],"some":[151],"pre-defined":[152],"constraint.":[154],"To":[155],"end,":[157],"we":[158,229],"propose":[159],"learn":[161],"global":[163],"ranking":[164],"across":[168],"different":[169,186,221],"layers":[170],"ConvNet,":[173],"is":[175,198],"used":[176],"obtain":[178],"architectures":[183],"that":[184],"have":[185,230],"accuracy/latency":[187],"bottom-ranked":[192],"filters.":[193],"Our":[194],"proposed":[195],"algorithm,":[196],"LeGR,":[197],"shown":[199],"2x":[202],"3x":[204],"faster":[205],"than":[206],"prior":[207],"while":[209],"having":[210],"comparable":[211],"better":[213],"when":[215],"seven":[217],"pruned":[218],"ResNet-56":[219],"accuracy/FLOPs":[222],"profiles":[223],"on":[224,233],"CIFAR-100":[226],"dataset.":[227],"Additionally,":[228],"evaluated":[231],"LeGR":[232],"ImageNet":[234],"Bird-200":[236],"ResNet-50":[238],"MobileNetV2":[240],"demonstrate":[242],"effectiveness.":[244],"Code":[245],"available":[246],"at":[247],"https":[249],"URL.":[250]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":6}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2019-05-03T00:00:00"}