{"id":"https://openalex.org/W2997943173","doi":"https://doi.org/10.1145/3336191.3371849","title":"Incremental Filter Pruning via Random Walk for Accelerating Deep Convolutional Neural Networks","display_name":"Incremental Filter Pruning via Random Walk for Accelerating Deep Convolutional Neural Networks","publication_year":2020,"publication_date":"2020-01-20","ids":{"openalex":"https://openalex.org/W2997943173","doi":"https://doi.org/10.1145/3336191.3371849","mag":"2997943173"},"language":"en","primary_location":{"id":"doi:10.1145/3336191.3371849","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3336191.3371849","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th International Conference on Web Search and Data Mining","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/A5107951448","display_name":"Qinghua Li","orcid":null},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qinghua Li","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100619237","display_name":"Cuiping Li","orcid":"https://orcid.org/0000-0003-0089-1045"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cuiping Li","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100420391","display_name":"Hong Chen","orcid":"https://orcid.org/0000-0001-8132-9382"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Chen","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5107951448"],"corresponding_institution_ids":["https://openalex.org/I78988378"],"apc_list":null,"apc_paid":null,"fwci":0.1954,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.4638536,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"358","last_page":"366"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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":0.9998000264167786,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9991999864578247,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.996999979019165,"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":0.7950356006622314},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7466043829917908},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.71795254945755},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6770168542861938},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5989347696304321},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.593492865562439},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5315924286842346},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.48895537853240967},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.46028462052345276},{"id":"https://openalex.org/keywords/random-walk","display_name":"Random walk","score":0.41207560896873474},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.38617396354675293},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37269896268844604},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34414634108543396},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.27088484168052673},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.17062118649482727},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.16034159064292908},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10249724984169006}],"concepts":[{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.7950356006622314},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7466043829917908},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.71795254945755},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6770168542861938},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5989347696304321},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.593492865562439},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5315924286842346},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.48895537853240967},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.46028462052345276},{"id":"https://openalex.org/C121194460","wikidata":"https://www.wikidata.org/wiki/Q856741","display_name":"Random walk","level":2,"score":0.41207560896873474},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38617396354675293},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37269896268844604},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34414634108543396},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.27088484168052673},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.17062118649482727},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.16034159064292908},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10249724984169006},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3336191.3371849","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3336191.3371849","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th International Conference on Web Search and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.75,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1935978687","https://openalex.org/W2072458630","https://openalex.org/W2096733369","https://openalex.org/W2114766824","https://openalex.org/W2117539524","https://openalex.org/W2125389748","https://openalex.org/W2126333738","https://openalex.org/W2147768505","https://openalex.org/W2194775991","https://openalex.org/W2302255633","https://openalex.org/W2554302513","https://openalex.org/W2604998962","https://openalex.org/W2608554408","https://openalex.org/W2798170643","https://openalex.org/W2798603777","https://openalex.org/W2807961551","https://openalex.org/W2808168148","https://openalex.org/W2808384944","https://openalex.org/W2808483802","https://openalex.org/W2962851801","https://openalex.org/W2962965870","https://openalex.org/W2963145730","https://openalex.org/W2963363373","https://openalex.org/W2963674932","https://openalex.org/W2963981420","https://openalex.org/W2964137095","https://openalex.org/W2964233199","https://openalex.org/W2964299589","https://openalex.org/W3099206234","https://openalex.org/W3104263540","https://openalex.org/W3177525997"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2146343568","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2013643406","https://openalex.org/W2027972911","https://openalex.org/W2157978810","https://openalex.org/W2597809628","https://openalex.org/W3005814217"],"abstract_inverted_index":{"Accelerating":[0],"Deep":[1],"Convolutional":[2],"Neural":[3],"Networks":[4],"(CNNs)":[5],"has":[6,21],"recently":[7],"received":[8],"ever-increasing":[9],"research":[10],"focus.":[11],"Among":[12],"various":[13],"approaches":[14],"proposed":[15],"in":[16,34,85],"the":[17,69,73,94,108,121,149,172,219],"literature,":[18],"filter":[19,110,136,221],"pruning":[20,61,137,153,222],"been":[22],"regarded":[23],"as":[24],"a":[25,82,134],"promising":[26],"solution,":[27],"which":[28,86,92,117,214],"is":[29,178],"due":[30],"to":[31,53,67,96,111,120,167],"its":[32],"advantage":[33],"significant":[35],"speedup":[36],"and":[37,44,62,113,157,174],"memory":[38],"reduction":[39],"of":[40,123,126,151,162,176],"both":[41],"network":[42],"model":[43,70,98],"intermediate":[45],"feature":[46],"maps.":[47],"Previous":[48,79,104],"works":[49,80,105],"utilized":[50],"\"smaller-norm-less-important\"":[51],"criterion":[52],"prune":[54],"filters":[55,88],"with":[56,191,208],"smaller":[57],"\u0841p-norm":[58],"values":[59],"by":[60,154,160],"retraining":[63],"alternately.":[64],"This":[65],"trends":[66],"narrow":[68],"capacity":[71],"for":[72],"following":[74],"reasons:":[75],"(1)":[76],"Violent":[77],"pruning.":[78],"adopt":[81],"violent":[83,152],"strategy":[84],"all":[87],"are":[89],"simultaneously":[90],"pruned,":[91],"leaving":[93],"room":[95],"retain":[97],"accuracy":[99,195],"limited.":[100],"(2)":[101],"Filter":[102,141,158],"degradation.":[103],"simply":[106],"set":[107],"pruned":[109],"0":[112],"retrained":[114],"it":[115],"alterately,":[116],"easily":[118],"led":[119],"loss":[122],"learning":[124],"ability":[125],"filters.":[127],"To":[128],"solve":[129],"this":[130],"problem,":[131],"we":[132],"propose":[133],"novel":[135],"method,":[138],"namely":[139],"Incremental":[140],"Pruning":[142],"via":[143],"Random":[144],"Walk":[145],"(IFPRW).":[146],"IFPRW":[147,177,183,200,217],"solves":[148],"problem":[150],"incremental":[155],"method":[156],"degradation":[159],"means":[161],"random":[163],"walk.":[164],"When":[165],"applied":[166],"two":[168],"image":[169],"classification":[170],"benchmarks,":[171],"usefulness":[173],"strength":[175],"validated.":[179],"Notably,":[180],"on":[181,189,198,206],"CIFAR-10,":[182],"reduces":[184,201],"more":[185,202],"than":[186,203],"46%":[187],"FLOPs":[188,205],"ResNet-110":[190],"even":[192],"0.28%":[193],"relative":[194],"improvement.":[196],"Moreover,":[197],"ILSVRC-2012,":[199],"54%":[204],"ResNet-101":[207],"only":[209],"0.7%":[210],"top-5":[211],"accurcacy":[212],"drop.":[213],"proving":[215],"that":[216],"outperforms":[218],"state-of-the-art":[220],"methods.":[223]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}