{"id":"https://openalex.org/W2899244816","doi":"https://doi.org/10.1609/aaai.v33i01.33015676","title":"Balanced Sparsity for Efficient DNN Inference on GPU","display_name":"Balanced Sparsity for Efficient DNN Inference on GPU","publication_year":2019,"publication_date":"2019-07-17","ids":{"openalex":"https://openalex.org/W2899244816","doi":"https://doi.org/10.1609/aaai.v33i01.33015676","mag":"2899244816"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v33i01.33015676","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33015676","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4512/4390","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4512/4390","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012287052","display_name":"Zhuliang Yao","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuliang Yao","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000260708","display_name":"Shi\u2010Jie Cao","orcid":"https://orcid.org/0000-0001-9136-0949"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shijie Cao","raw_affiliation_strings":["Harbin Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086945155","display_name":"Wencong Xiao","orcid":"https://orcid.org/0000-0002-3043-522X"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wencong Xiao","raw_affiliation_strings":["Beihang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100374175","display_name":"Chen Zhang","orcid":"https://orcid.org/0000-0003-2762-2726"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Zhang","raw_affiliation_strings":["Microsoft Research Asia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100642163","display_name":"Lanshun Nie","orcid":"https://orcid.org/0000-0002-8354-8359"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lanshun Nie","raw_affiliation_strings":["Harbin Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":81,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":"01","first_page":"5676","last_page":"5683"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T11609","display_name":"Geophysical Methods and Applications","score":0.9973000288009644,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.8571170568466187},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8522465229034424},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.8310809135437012},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.7719417214393616},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5689472556114197},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5358695983886719},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.46765321493148804},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.455144464969635},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4242652356624603},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.34902530908584595},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33501848578453064}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.8571170568466187},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8522465229034424},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.8310809135437012},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.7719417214393616},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5689472556114197},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5358695983886719},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.46765321493148804},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.455144464969635},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4242652356624603},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34902530908584595},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33501848578453064},{"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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1609/aaai.v33i01.33015676","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33015676","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4512/4390","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1811.00206","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1811.00206","pdf_url":"https://arxiv.org/pdf/1811.00206","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_type":"text"},{"id":"pmh:oai:ojs.aaai.org:article/4512","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/4512","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v33i01.33015676","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33015676","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4512/4390","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3346008664","display_name":null,"funder_award_id":"No.61772159","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8286498368","display_name":"\u591a\u7ef4\u5927\u6570\u636e\u9a71\u52a8\u7684\u670d\u52a1\u4f18\u5316\u7ec4\u5408\u7406\u8bba\u4e0e\u65b9\u6cd5\u7814\u7a76","funder_award_id":"61772159","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320308943","display_name":"Microsoft Research","ror":"https://ror.org/00d0nc645"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320333993","display_name":"Microsoft Research Asia","ror":"https://ror.org/0300m5276"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2899244816.pdf","grobid_xml":"https://content.openalex.org/works/W2899244816.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W1530262073","https://openalex.org/W1686810756","https://openalex.org/W1719489212","https://openalex.org/W1935978687","https://openalex.org/W1996901117","https://openalex.org/W2106721790","https://openalex.org/W2153827974","https://openalex.org/W2163605009","https://openalex.org/W2164411961","https://openalex.org/W2284050935","https://openalex.org/W2488497244","https://openalex.org/W2553910756","https://openalex.org/W2617991662","https://openalex.org/W2619096655","https://openalex.org/W2737121650","https://openalex.org/W2751438535","https://openalex.org/W2752037867","https://openalex.org/W2754526845","https://openalex.org/W2757143157","https://openalex.org/W2764043458","https://openalex.org/W2767785892","https://openalex.org/W2950656546","https://openalex.org/W2952682304","https://openalex.org/W2962963202","https://openalex.org/W2962965870","https://openalex.org/W2963000224","https://openalex.org/W2963363373","https://openalex.org/W2963416938","https://openalex.org/W2963981420","https://openalex.org/W4292564261","https://openalex.org/W4297699616","https://openalex.org/W4297813615","https://openalex.org/W6640289440","https://openalex.org/W6677103964","https://openalex.org/W6684488266","https://openalex.org/W6724998850","https://openalex.org/W6725543821","https://openalex.org/W6743912273","https://openalex.org/W7027429494"],"related_works":["https://openalex.org/W2097707447","https://openalex.org/W4377865163","https://openalex.org/W4287323461","https://openalex.org/W3042419602","https://openalex.org/W2966649771","https://openalex.org/W3193857078","https://openalex.org/W2888956734","https://openalex.org/W3000197790","https://openalex.org/W4315865067","https://openalex.org/W2979433843"],"abstract_inverted_index":{"In":[0,56],"trained":[1],"deep":[2,96],"neural":[3],"networks,":[4],"unstructured":[5],"pruning":[6],"can":[7],"reduce":[8],"redundant":[9],"weights":[10,45],"to":[11,22,40,68,80,107],"lower":[12],"storage":[13],"cost.":[14],"However,":[15],"it":[16],"requires":[17],"the":[18,92,118],"customization":[19],"of":[20,84,95],"hardwares":[21,35,75],"speed":[23],"up":[24,106],"practical":[25,109],"inference.":[26],"Another":[27],"trend":[28],"accelerates":[29],"sparse":[30],"model":[31,54,71,112,121],"inference":[32,113],"on":[33,114],"general-purpose":[34],"by":[36],"adopting":[37],"coarse-grained":[38],"sparsity":[39,64,90],"prune":[41],"or":[42],"regularize":[43],"consecutive":[44],"for":[46,89,111],"efficient":[47],"computation.":[48],"But":[49],"this":[50,57],"method":[51],"often":[52],"sacrifices":[53],"accuracy.":[55],"paper,":[58],"we":[59],"propose":[60],"a":[61],"novel":[62],"fine-grained":[63],"approach,":[65],"Balanced":[66,103],"Sparsity,":[67],"achieve":[69],"high":[70,81,120],"accuracy":[72,122],"with":[73],"commercial":[74],"efficiently.":[76],"Our":[77],"approach":[78],"adapts":[79],"parallelism":[82],"property":[83],"GPU,":[85,115],"showing":[86],"incredible":[87],"potential":[88],"in":[91],"widely":[93],"deployment":[94],"learning":[97],"services.":[98],"Experiment":[99],"results":[100],"show":[101],"that":[102],"Sparsity":[104],"achieves":[105],"3.1x":[108],"speedup":[110],"while":[116],"retains":[117],"same":[119],"as":[123],"finegrained":[124],"sparsity.":[125]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":23},{"year":2020,"cited_by_count":16},{"year":2019,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2019-06-27T00:00:00"}