{"id":"https://openalex.org/W3203332826","doi":"https://doi.org/10.1145/3466752.3480120","title":"Shift-BNN: Highly-Efficient Probabilistic Bayesian Neural Network Training via Memory-Friendly Pattern Retrieving","display_name":"Shift-BNN: Highly-Efficient Probabilistic Bayesian Neural Network Training via Memory-Friendly Pattern Retrieving","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3203332826","doi":"https://doi.org/10.1145/3466752.3480120","mag":"3203332826"},"language":"en","primary_location":{"id":"doi:10.1145/3466752.3480120","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3466752.3480120","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"MICRO-54: 54th Annual IEEE/ACM International Symposium on Microarchitecture","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2110.03553","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056956005","display_name":"Qiyu Wan","orcid":"https://orcid.org/0000-0001-8529-5175"},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Qiyu Wan","raw_affiliation_strings":["University of Houston"],"affiliations":[{"raw_affiliation_string":"University of Houston","institution_ids":["https://openalex.org/I44461941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005527086","display_name":"Haojun Xia","orcid":"https://orcid.org/0000-0002-9384-0935"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Haojun Xia","raw_affiliation_strings":["University of Sydney"],"affiliations":[{"raw_affiliation_string":"University of Sydney","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010481801","display_name":"Xingyao Zhang","orcid":"https://orcid.org/0000-0002-8874-9520"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xingyao Zhang","raw_affiliation_strings":["University of Washington, United States of America"],"affiliations":[{"raw_affiliation_string":"University of Washington, United States of America","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024150524","display_name":"Lening Wang","orcid":"https://orcid.org/0000-0001-7717-1199"},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lening Wang","raw_affiliation_strings":["University of Houston, United States of America"],"affiliations":[{"raw_affiliation_string":"University of Houston, United States of America","institution_ids":["https://openalex.org/I44461941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043209884","display_name":"Shuaiwen Leon Song","orcid":"https://orcid.org/0000-0002-8402-1436"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Shuaiwen Leon Song","raw_affiliation_strings":["University of Sydney and UW Seattle, Australia"],"affiliations":[{"raw_affiliation_string":"University of Sydney and UW Seattle, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016298390","display_name":"Xin Fu","orcid":"https://orcid.org/0000-0002-9458-4769"},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xin Fu","raw_affiliation_strings":["University of Houston"],"affiliations":[{"raw_affiliation_string":"University of Houston","institution_ids":["https://openalex.org/I44461941"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5056956005"],"corresponding_institution_ids":["https://openalex.org/I44461941"],"apc_list":null,"apc_paid":null,"fwci":0.9786,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.808763,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"885","last_page":"897"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.998199999332428,"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"}},"topics":[{"id":"https://openalex.org/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.998199999332428,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9976999759674072,"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":0.9970999956130981,"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":0.7618567943572998},{"id":"https://openalex.org/keywords/bayesian-network","display_name":"Bayesian network","score":0.6277542114257812},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6041127443313599},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6012033224105835},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5657247304916382},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5430812239646912},{"id":"https://openalex.org/keywords/probabilistic-neural-network","display_name":"Probabilistic neural network","score":0.4671672582626343},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.4285290539264679},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4281895160675049},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3339911699295044},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.2875092923641205}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7618567943572998},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.6277542114257812},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6041127443313599},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6012033224105835},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5657247304916382},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5430812239646912},{"id":"https://openalex.org/C134342201","wikidata":"https://www.wikidata.org/wiki/Q7246859","display_name":"Probabilistic neural network","level":4,"score":0.4671672582626343},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.4285290539264679},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4281895160675049},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3339911699295044},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.2875092923641205},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3466752.3480120","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3466752.3480120","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"MICRO-54: 54th Annual IEEE/ACM International Symposium on Microarchitecture","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2110.03553","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2110.03553","pdf_url":"https://arxiv.org/pdf/2110.03553","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2110.03553","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2110.03553","pdf_url":"https://arxiv.org/pdf/2110.03553","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"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.8999999761581421,"display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G8333557126","display_name":null,"funder_award_id":"CCF-1900904","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":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":78,"referenced_works":["https://openalex.org/W582134693","https://openalex.org/W1502034661","https://openalex.org/W1686810756","https://openalex.org/W1744759976","https://openalex.org/W1841592590","https://openalex.org/W1983406208","https://openalex.org/W1990315422","https://openalex.org/W1999085092","https://openalex.org/W2007339694","https://openalex.org/W2066708466","https://openalex.org/W2067523571","https://openalex.org/W2102074146","https://openalex.org/W2103328396","https://openalex.org/W2108598243","https://openalex.org/W2108677974","https://openalex.org/W2130306094","https://openalex.org/W2150947797","https://openalex.org/W2152839228","https://openalex.org/W2156303437","https://openalex.org/W2164411961","https://openalex.org/W2166851633","https://openalex.org/W2194775991","https://openalex.org/W2225156818","https://openalex.org/W2249651582","https://openalex.org/W2287011250","https://openalex.org/W2342840547","https://openalex.org/W2442974303","https://openalex.org/W2462906003","https://openalex.org/W2489529491","https://openalex.org/W2495112539","https://openalex.org/W2545581649","https://openalex.org/W2618530766","https://openalex.org/W2626991402","https://openalex.org/W2782718222","https://openalex.org/W2785369415","https://openalex.org/W2799977193","https://openalex.org/W2803113791","https://openalex.org/W2808310312","https://openalex.org/W2889797931","https://openalex.org/W2906043559","https://openalex.org/W2910171846","https://openalex.org/W2949866178","https://openalex.org/W2951965145","https://openalex.org/W2952186347","https://openalex.org/W2953235111","https://openalex.org/W2962851448","https://openalex.org/W2963358710","https://openalex.org/W2963374099","https://openalex.org/W2963709416","https://openalex.org/W2964059111","https://openalex.org/W2964174152","https://openalex.org/W2979515806","https://openalex.org/W2979754840","https://openalex.org/W2987612038","https://openalex.org/W2990765879","https://openalex.org/W2999599167","https://openalex.org/W3016542674","https://openalex.org/W3043619075","https://openalex.org/W3093859587","https://openalex.org/W3098989436","https://openalex.org/W3099584108","https://openalex.org/W3101380508","https://openalex.org/W3101788429","https://openalex.org/W3102167048","https://openalex.org/W3102587717","https://openalex.org/W3103894541","https://openalex.org/W3105802176","https://openalex.org/W3118608800","https://openalex.org/W4239072543","https://openalex.org/W4251999575","https://openalex.org/W4253012315","https://openalex.org/W4288093264","https://openalex.org/W4294562888","https://openalex.org/W4295312788","https://openalex.org/W4297804357","https://openalex.org/W4299788010","https://openalex.org/W4301361180","https://openalex.org/W4309299128"],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W3216976533","https://openalex.org/W100620283","https://openalex.org/W1734881440","https://openalex.org/W1991381172","https://openalex.org/W2988849960"],"abstract_inverted_index":{"Bayesian":[0],"Neural":[1],"Networks":[2],"(BNNs)":[3],"that":[4,74,103,178,191],"possess":[5],"a":[6,16,41,65,100],"property":[7],"of":[8,19,40,49,56,60,116,144,196],"uncertainty":[9],"estimation":[10],"have":[11],"been":[12],"increasingly":[13],"adopted":[14],"in":[15,204],"wide":[17],"range":[18],"safety-critical":[20],"AI":[21],"applications":[22],"which":[23,53],"demand":[24],"reliable":[25],"and":[26,149,167,181,207],"robust":[27],"decision":[28],"making,":[29],"e.g.,":[30],"self-driving,":[31],"rescue":[32],"robots,":[33],"medical":[34],"image":[35],"diagnosis.":[36],"The":[37],"training":[38,46,64,80,125,174,219],"procedure":[39],"probabilistic":[42],"BNN":[43,79,173,188],"model":[44],"involves":[45],"an":[47,194],"ensemble":[48],"sampled":[50],"DNN":[51,67,147,218],"models,":[52],"induces":[54],"orders":[55],"magnitude":[57],"larger":[58],"volume":[59],"data":[61,87,108],"movement":[62],"than":[63],"single":[66],"model.":[68],"In":[69],"this":[70,96,163],"paper,":[71],"we":[72,98,139,165],"reveal":[73],"the":[75,84,106,113,136,141,145,151,169,216],"root":[76],"cause":[77],"for":[78],"inefficiency":[81],"originates":[82],"from":[83],"massive":[85],"off-chip":[86,107],"transfer":[88,109],"by":[89,110],"Gaussian":[90],"Random":[91],"Variables":[92],"(GRVs).":[93],"To":[94,128],"tackle":[95],"challenge,":[97],"propose":[99],"novel":[101],"design":[102,142,166],"eliminates":[104],"all":[105],"GRVs":[111],"through":[112],"reversed":[114],"shifting":[115],"Linear":[117],"Feedback":[118],"Shift":[119],"Registers":[120],"(LFSRs)":[121],"without":[122],"incurring":[123],"any":[124],"accuracy":[126],"loss.":[127],"efficiently":[129],"support":[130],"our":[131,159],"LFSR":[132],"reversion":[133],"strategy":[134],"at":[135],"hardware":[137],"level,":[138],"explore":[140],"space":[143],"current":[146],"accelerators":[148],"identify":[150],"optimal":[152],"computation":[153],"mapping":[154],"scheme":[155],"to":[156,200,211],"best":[157],"accommodate":[158],"strategy.":[160],"By":[161],"leveraging":[162],"finding,":[164],"prototype":[168],"first":[170],"highly":[171],"efficient":[172],"accelerator,":[175],"named":[176],"Shift-BNN,":[177],"is":[179],"low-cost":[180],"scalable.":[182],"Extensive":[183],"evaluation":[184],"on":[185],"five":[186],"representative":[187],"models":[189],"demonstrates":[190],"Shift-BNN":[192],"achieves":[193],"average":[195],"4.9":[197],"\u00d7":[198,209],"(up":[199,210],"10.8":[201],"\u00d7)":[202,213],"boost":[203],"energy":[205],"efficiency":[206],"1.6":[208],"2.8":[212],"speedup":[214],"over":[215],"baseline":[217],"accelerator.":[220]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2021-10-11T00:00:00"}