{"id":"https://openalex.org/W4200630931","doi":"https://doi.org/10.24963/ijcai.2022/449","title":"Pruning-as-Search: Efficient Neural Architecture Search via Channel Pruning and Structural Reparameterization","display_name":"Pruning-as-Search: Efficient Neural Architecture Search via Channel Pruning and Structural Reparameterization","publication_year":2022,"publication_date":"2022-07-01","ids":{"openalex":"https://openalex.org/W4200630931","doi":"https://doi.org/10.24963/ijcai.2022/449"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2022/449","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/449","pdf_url":"https://www.ijcai.org/proceedings/2022/0449.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2022/0449.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010773732","display_name":"Yanyu Li","orcid":"https://orcid.org/0000-0003-1240-4785"},"institutions":[{"id":"https://openalex.org/I87182695","display_name":"Universidad del Noreste","ror":"https://ror.org/02ahky613","country_code":"MX","type":"education","lineage":["https://openalex.org/I87182695"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Yanyu Li","raw_affiliation_strings":["Northeastern University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University","institution_ids":["https://openalex.org/I87182695"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113115311","display_name":"Pu Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I87182695","display_name":"Universidad del Noreste","ror":"https://ror.org/02ahky613","country_code":"MX","type":"education","lineage":["https://openalex.org/I87182695"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Pu Zhao","raw_affiliation_strings":["Northeastern University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University","institution_ids":["https://openalex.org/I87182695"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100957385","display_name":"Geng Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I87182695","display_name":"Universidad del Noreste","ror":"https://ror.org/02ahky613","country_code":"MX","type":"education","lineage":["https://openalex.org/I87182695"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Geng Yuan","raw_affiliation_strings":["Northeastern University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University","institution_ids":["https://openalex.org/I87182695"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043582832","display_name":"Xue Lin","orcid":"https://orcid.org/0000-0001-6210-8883"},"institutions":[{"id":"https://openalex.org/I87182695","display_name":"Universidad del Noreste","ror":"https://ror.org/02ahky613","country_code":"MX","type":"education","lineage":["https://openalex.org/I87182695"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Xue Lin","raw_affiliation_strings":["Northeastern University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University","institution_ids":["https://openalex.org/I87182695"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100651384","display_name":"Yanzhi Wang","orcid":"https://orcid.org/0000-0002-3024-7990"},"institutions":[{"id":"https://openalex.org/I87182695","display_name":"Universidad del Noreste","ror":"https://ror.org/02ahky613","country_code":"MX","type":"education","lineage":["https://openalex.org/I87182695"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Yanzhi Wang","raw_affiliation_strings":["Northeastern University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University","institution_ids":["https://openalex.org/I87182695"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100363023","display_name":"Xin Chen","orcid":"https://orcid.org/0000-0001-6177-4032"},"institutions":[{"id":"https://openalex.org/I4210158342","display_name":"Intel (United Kingdom)","ror":"https://ror.org/058cxws58","country_code":"GB","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210158342"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xin Chen","raw_affiliation_strings":["Intel Corp"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Corp","institution_ids":["https://openalex.org/I4210158342"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.7738,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.93546256,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3236","last_page":"3242"},"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":0.9995999932289124,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9988999962806702,"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/pruning","display_name":"Pruning","score":0.8609873652458191},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7388006448745728},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5991251468658447},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5121724605560303},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5048671364784241},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4897651672363281},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.41608676314353943},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.41488611698150635},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3826308846473694},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36017799377441406}],"concepts":[{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.8609873652458191},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7388006448745728},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5991251468658447},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5121724605560303},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5048671364784241},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4897651672363281},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.41608676314353943},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.41488611698150635},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3826308846473694},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36017799377441406},{"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/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:10.24963/ijcai.2022/449","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/449","pdf_url":"https://www.ijcai.org/proceedings/2022/0449.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2022/449","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/449","pdf_url":"https://www.ijcai.org/proceedings/2022/0449.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.44999998807907104,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G1332542428","display_name":"RTML: Large: Efficient and Adaptive Real-Time Learning for Next Generation Wireless Systems","funder_award_id":"1937500","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2587219159","display_name":"SHF: Medium: Collaborative Research: ADMM-NN: A Unified Software/Hardware Framework of DNN Computation and Storage Reduction Using ADMM","funder_award_id":"1901378","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2894394386","display_name":null,"funder_award_id":"W911-NF-20-1-0167","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G5182725229","display_name":null,"funder_award_id":"W911-NF-20-1-0167","funder_id":"https://openalex.org/F4320338295","funder_display_name":"Army Research Laboratory"},{"id":"https://openalex.org/G7940815196","display_name":null,"funder_award_id":"CCF-1937500","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8912281322","display_name":null,"funder_award_id":"CCF-1901378","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"},{"id":"https://openalex.org/F4320306078","display_name":"U.S. Department of Defense","ror":"https://ror.org/0447fe631"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"},{"id":"https://openalex.org/F4320338295","display_name":"Army Research Laboratory","ror":"https://ror.org/011hc8f90"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4200630931.pdf","grobid_xml":"https://content.openalex.org/works/W4200630931.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2242818861","https://openalex.org/W2495425901","https://openalex.org/W2553303224","https://openalex.org/W2788852320","https://openalex.org/W2796265726","https://openalex.org/W2924498682","https://openalex.org/W2945335799","https://openalex.org/W2949941638","https://openalex.org/W2951104886","https://openalex.org/W2955425717","https://openalex.org/W2962793481","https://openalex.org/W2962851801","https://openalex.org/W2963163009","https://openalex.org/W2963363373","https://openalex.org/W2963918968","https://openalex.org/W2964076515","https://openalex.org/W2964233199","https://openalex.org/W2967733054","https://openalex.org/W2984618279","https://openalex.org/W2993182889","https://openalex.org/W3035377608","https://openalex.org/W3097855639","https://openalex.org/W3167976421","https://openalex.org/W3177640626","https://openalex.org/W3196865505","https://openalex.org/W4225547403","https://openalex.org/W4287178479","https://openalex.org/W4297813615","https://openalex.org/W4309845474","https://openalex.org/W4320930577"],"related_works":["https://openalex.org/W4293226380","https://openalex.org/W2373300491","https://openalex.org/W4375867731","https://openalex.org/W2395294869","https://openalex.org/W4226493464","https://openalex.org/W4312417841","https://openalex.org/W3133861977","https://openalex.org/W2951211570","https://openalex.org/W3103566983","https://openalex.org/W3029198973"],"abstract_inverted_index":{"Neural":[0],"architecture":[1,21,130],"search":[2,25,67,155],"(NAS)":[3],"and":[4,45,57,72,94,105,162,166],"network":[5],"pruning":[6,29,64,83],"are":[7,168],"widely":[8],"studied":[9],"efficient":[10],"AI":[11],"techniques,":[12],"but":[13],"not":[14],"yet":[15],"perfect.":[16],"NAS":[17],"performs":[18],"exhaustive":[19],"candidate":[20],"search,":[22],"incurring":[23],"tremendous":[24],"cost.":[26],"Though":[27],"(structured)":[28],"can":[30],"simply":[31],"shrink":[32],"model":[33],"dimension,":[34],"it":[35],"remains":[36],"unclear":[37],"how":[38],"to":[39,66,81,117],"decide":[40],"the":[41,52,91,110,150],"per-layer":[42],"sparsity":[43],"automatically":[44,71],"optimally.":[46],"In":[47],"this":[48],"work,":[49],"we":[50,75,96,148],"revisit":[51],"problem":[53],"of":[54,103,112,121,152],"layer-width":[55],"optimization":[56],"propose":[58],"Pruning-as-Search":[59],"(PaS),":[60],"an":[61],"end-to-end":[62],"channel":[63],"method":[65],"out":[68,99],"desired":[69],"sub-network":[70],"efficiently.":[73],"Specifically,":[74],"add":[76],"a":[77,100],"depth-wise":[78],"binary":[79],"convolution":[80],"learn":[82],"policies":[84],"directly":[85],"through":[86],"gradient":[87],"descent.":[88],"By":[89],"combining":[90],"structural":[92],"reparameterization":[93],"PaS,":[95],"successfully":[97],"searched":[98],"new":[101],"family":[102],"VGG-like":[104],"lightweight":[106],"networks,":[107],"which":[108],"enable":[109],"flexibility":[111],"arbitrary":[113],"width":[114,154],"with":[115],"respect":[116],"each":[118,122],"layer":[119],"instead":[120],"stage.":[123],"Experimental":[124],"results":[125],"show":[126],"that":[127],"our":[128,153],"proposed":[129],"outperforms":[131],"prior":[132],"arts":[133],"by":[134],"around":[135],"1.0%":[136],"top-1":[137],"accuracy":[138],"under":[139],"similar":[140],"inference":[141],"speed":[142],"on":[143,156],"ImageNet-1000":[144],"classification":[145],"task.":[146],"Furthermore,":[147],"demonstrate":[149],"effectiveness":[151],"complex":[157],"tasks":[158],"including":[159],"instance":[160],"segmentation":[161],"image":[163],"translation.":[164],"Code":[165],"models":[167],"released.":[169]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":6}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}