{"id":"https://openalex.org/W4287322404","doi":"https://doi.org/10.1109/bigdata55660.2022.10020972","title":"Efficient Soft-Error Detection for Low-precision Deep Learning Recommendation Models","display_name":"Efficient Soft-Error Detection for Low-precision Deep Learning Recommendation Models","publication_year":2022,"publication_date":"2022-12-17","ids":{"openalex":"https://openalex.org/W4287322404","doi":"https://doi.org/10.1109/bigdata55660.2022.10020972"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata55660.2022.10020972","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata55660.2022.10020972","pdf_url":null,"source":{"id":"https://openalex.org/S4363607709","display_name":"2022 IEEE International Conference on Big Data (Big Data)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Big Data (Big Data)","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/A5103179545","display_name":"Sihuan Li","orcid":"https://orcid.org/0000-0001-7315-7955"},"institutions":[{"id":"https://openalex.org/I4210092558","display_name":"BC Platforms (Finland)","ror":"https://ror.org/002fen565","country_code":"FI","type":"company","lineage":["https://openalex.org/I4210092558"]},{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["FI","US"],"is_corresponding":true,"raw_author_name":"Sihuan Li","raw_affiliation_strings":["Meta Platforms, Inc"],"affiliations":[{"raw_affiliation_string":"Meta Platforms, Inc","institution_ids":["https://openalex.org/I4210092558","https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101717259","display_name":"Jianyu Huang","orcid":"https://orcid.org/0000-0001-7595-5539"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]},{"id":"https://openalex.org/I4210092558","display_name":"BC Platforms (Finland)","ror":"https://ror.org/002fen565","country_code":"FI","type":"company","lineage":["https://openalex.org/I4210092558"]}],"countries":["FI","US"],"is_corresponding":false,"raw_author_name":"Jianyu Huang","raw_affiliation_strings":["Meta Platforms, Inc"],"affiliations":[{"raw_affiliation_string":"Meta Platforms, Inc","institution_ids":["https://openalex.org/I4210092558","https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101748090","display_name":"Ping Tang","orcid":"https://orcid.org/0000-0002-8721-4209"},"institutions":[{"id":"https://openalex.org/I4210092558","display_name":"BC Platforms (Finland)","ror":"https://ror.org/002fen565","country_code":"FI","type":"company","lineage":["https://openalex.org/I4210092558"]},{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["FI","US"],"is_corresponding":false,"raw_author_name":"Ping Tak Peter Tang","raw_affiliation_strings":["Meta Platforms, Inc"],"affiliations":[{"raw_affiliation_string":"Meta Platforms, Inc","institution_ids":["https://openalex.org/I4210092558","https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060661843","display_name":"Daya Shanker Khudia","orcid":"https://orcid.org/0000-0002-6706-5074"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daya Khudia","raw_affiliation_strings":["MosaicML, Inc"],"affiliations":[{"raw_affiliation_string":"MosaicML, Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101876582","display_name":"Jongsoo Park","orcid":"https://orcid.org/0000-0002-4750-9440"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]},{"id":"https://openalex.org/I4210092558","display_name":"BC Platforms (Finland)","ror":"https://ror.org/002fen565","country_code":"FI","type":"company","lineage":["https://openalex.org/I4210092558"]}],"countries":["FI","US"],"is_corresponding":false,"raw_author_name":"Jongsoo Park","raw_affiliation_strings":["Meta Platforms, Inc"],"affiliations":[{"raw_affiliation_string":"Meta Platforms, Inc","institution_ids":["https://openalex.org/I4210092558","https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018336899","display_name":"Harish Dattatraya Dixit","orcid":"https://orcid.org/0009-0001-1163-5568"},"institutions":[{"id":"https://openalex.org/I4210092558","display_name":"BC Platforms (Finland)","ror":"https://ror.org/002fen565","country_code":"FI","type":"company","lineage":["https://openalex.org/I4210092558"]},{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["FI","US"],"is_corresponding":false,"raw_author_name":"Harish Dattatraya Dixit","raw_affiliation_strings":["Meta Platforms, Inc"],"affiliations":[{"raw_affiliation_string":"Meta Platforms, Inc","institution_ids":["https://openalex.org/I4210092558","https://openalex.org/I4210114444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061737717","display_name":"Zizhong Chen","orcid":"https://orcid.org/0000-0003-2578-4940"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zizhong Chen","raw_affiliation_strings":["University of California,Riverside,CA,USA","University of California, Riverside, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California,Riverside,CA,USA","institution_ids":["https://openalex.org/I103635307"]},{"raw_affiliation_string":"University of California, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5103179545"],"corresponding_institution_ids":["https://openalex.org/I4210092558","https://openalex.org/I4210114444"],"apc_list":null,"apc_paid":null,"fwci":4.503,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.96608565,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1556","last_page":"1563"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11005","display_name":"Radiation Effects in Electronics","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11005","display_name":"Radiation Effects in Electronics","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9965999722480774,"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/T10363","display_name":"Low-power high-performance VLSI design","score":0.993399977684021,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/computer-science","display_name":"Computer science","score":0.7776305079460144},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6226390600204468},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5546961426734924},{"id":"https://openalex.org/keywords/false-positive-paradox","display_name":"False positive paradox","score":0.4941294491291046},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4935377836227417},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.48515328764915466},{"id":"https://openalex.org/keywords/error-detection-and-correction","display_name":"Error detection and correction","score":0.48483335971832275},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4778042435646057},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.43083709478378296},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.4167572557926178},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4023315906524658},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3317767381668091}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7776305079460144},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6226390600204468},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5546961426734924},{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.4941294491291046},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4935377836227417},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.48515328764915466},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.48483335971832275},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4778042435646057},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.43083709478378296},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.4167572557926178},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4023315906524658},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3317767381668091},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata55660.2022.10020972","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata55660.2022.10020972","pdf_url":null,"source":{"id":"https://openalex.org/S4363607709","display_name":"2022 IEEE International Conference on Big Data (Big Data)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.8100000023841858}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320332359","display_name":"Office of Science","ror":"https://ror.org/00mmn6b08"},{"id":"https://openalex.org/F4320337506","display_name":"Advanced Scientific Computing Research","ror":"https://ror.org/0012c7r22"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1493774699","https://openalex.org/W2034593585","https://openalex.org/W2035492130","https://openalex.org/W2052455844","https://openalex.org/W2083613288","https://openalex.org/W2108434125","https://openalex.org/W2152212524","https://openalex.org/W2152652532","https://openalex.org/W2156514327","https://openalex.org/W2296204683","https://openalex.org/W2412349256","https://openalex.org/W2418331349","https://openalex.org/W2485331474","https://openalex.org/W2580243656","https://openalex.org/W2770542984","https://openalex.org/W2798289565","https://openalex.org/W2901848761","https://openalex.org/W2963122961","https://openalex.org/W2984020950","https://openalex.org/W2986514577","https://openalex.org/W3007788310","https://openalex.org/W3010969086","https://openalex.org/W3014034225","https://openalex.org/W3105862567","https://openalex.org/W3118280765","https://openalex.org/W3120931476","https://openalex.org/W3130104841","https://openalex.org/W3135074210","https://openalex.org/W4230550535","https://openalex.org/W4233447799","https://openalex.org/W4248621761","https://openalex.org/W4386212580","https://openalex.org/W6745384015","https://openalex.org/W6745889759","https://openalex.org/W6770169410","https://openalex.org/W6774806506","https://openalex.org/W6788597507"],"related_works":["https://openalex.org/W1557094818","https://openalex.org/W2183246718","https://openalex.org/W2099261052","https://openalex.org/W3209204065","https://openalex.org/W2105707930","https://openalex.org/W1755711892","https://openalex.org/W2160907113","https://openalex.org/W2394408226","https://openalex.org/W4389168214","https://openalex.org/W4366457933"],"abstract_inverted_index":{"Soft":[0,24],"error,":[1],"namely":[2],"silent":[3],"corruption":[4],"of":[5,33,61,84,123,157],"signal":[6],"or":[7],"datum":[8],"in":[9,30,41,92,150],"a":[10],"computer":[11],"system,":[12],"cannot":[13],"be":[14],"caverlierly":[15],"ignored":[16],"as":[17],"compute":[18],"and":[19,38,58,99,107,127],"communication":[20],"density":[21],"grow":[22],"exponentially.":[23],"error":[25,68,106],"detection":[26,69,86,135,152],"has":[27],"been":[28],"studied":[29],"the":[31,76,81,121,128],"context":[32],"enterprise":[34],"computing,":[35],"high-performance":[36],"computing":[37],"more":[39,132],"recently":[40],"convolutional":[42],"neural":[43],"networks":[44],"related":[45],"to":[46],"autonomous":[47],"driving.Deep":[48],"learning":[49],"recommendation":[50],"systems":[51],"(DLRMs)":[52],"have":[53],"by":[54],"now":[55],"become":[56],"ubiquitous":[57],"serve":[59],"billions":[60],"users":[62],"per":[63],"day.":[64],"Nevertheless,":[65],"DLRM-specific":[66],"soft":[67],"methods":[70,87],"are":[71],"hitherto":[72],"missing.":[73],"To":[74],"fill":[75],"gap,":[77],"this":[78],"paper":[79],"presents":[80],"first":[82],"set":[83],"soft-error":[85],"for":[88,137],"low-precision":[89],"quantized-arithmetic":[90],"operators":[91],"DLRM":[93],"including":[94],"general":[95],"matrix":[96],"multiplication":[97],"(GEMM)":[98],"EmbeddingBag.":[100],"A":[101],"practical":[102],"method":[103],"must":[104],"detect":[105],"do":[108],"so":[109],"with":[110,139,153],"low":[111],"overhead":[112,141,162],"lest":[113],"reduced":[114],"inference":[115],"speed":[116],"degrades":[117],"user":[118],"experience.":[119],"Exploiting":[120],"characteristics":[122],"both":[124],"quantized":[125],"arithmetic":[126],"operators,":[129],"we":[130,146],"achieved":[131,147],"than":[133,155],"95%":[134],"accuracy":[136],"GEMM":[138],"an":[140],"below":[142,163],"20%.":[143],"For":[144],"EmbeddingBag,":[145],"99%":[148],"effectiveness":[149],"significant-bit-flips":[151],"less":[154],"10%":[156],"false":[158],"positives,":[159],"while":[160],"keeping":[161],"26%.":[164]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-13T16:22:10.518609","created_date":"2025-10-10T00:00:00"}