{"id":"https://openalex.org/W4396910092","doi":"https://doi.org/10.1109/ojcs.2024.3400696","title":"ALBERTA: ALgorithm-Based Error Resilience in Transformer Architectures","display_name":"ALBERTA: ALgorithm-Based Error Resilience in Transformer Architectures","publication_year":2024,"publication_date":"2024-05-14","ids":{"openalex":"https://openalex.org/W4396910092","doi":"https://doi.org/10.1109/ojcs.2024.3400696"},"language":"en","primary_location":{"id":"doi:10.1109/ojcs.2024.3400696","is_oa":true,"landing_page_url":"https://doi.org/10.1109/ojcs.2024.3400696","pdf_url":"https://ieeexplore.ieee.org/ielx7/8782664/9024218/10530530.pdf","source":{"id":"https://openalex.org/S4210176459","display_name":"IEEE Open Journal of the Computer Society","issn_l":"2644-1268","issn":["2644-1268"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Open Journal of the Computer Society","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/8782664/9024218/10530530.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107384045","display_name":"H. Liu","orcid":"https://orcid.org/0009-0007-8041-1596"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Haoxuan Liu","raw_affiliation_strings":["NVIDIA, Santa Clara, CA, USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001418143","display_name":"Vasu Singh","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vasu Singh","raw_affiliation_strings":["NVIDIA, Santa Clara, CA, USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015464542","display_name":"Micha\u0142 Filipiuk","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Micha\u0142 Filipiuk","raw_affiliation_strings":["NVIDIA, Santa Clara, CA, USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054590774","display_name":"Siva Kumar Sastry Hari","orcid":"https://orcid.org/0000-0001-8346-7981"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siva Kumar Sastry Hari","raw_affiliation_strings":["NVIDIA, Santa Clara, CA, USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210127875"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5107384045"],"corresponding_institution_ids":["https://openalex.org/I4210127875"],"apc_list":{"value":1750,"currency":"USD","value_usd":1750},"apc_paid":{"value":1750,"currency":"USD","value_usd":1750},"fwci":1.5196,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.82264491,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"6","issue":null,"first_page":"85","last_page":"96"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11343","display_name":"Power Transformer Diagnostics and Insulation","score":0.9909999966621399,"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/T11343","display_name":"Power Transformer Diagnostics and Insulation","score":0.9909999966621399,"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/T10972","display_name":"Power Systems Fault Detection","score":0.9883000254631042,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T11941","display_name":"Power System Reliability and Maintenance","score":0.9860000014305115,"subfield":{"id":"https://openalex.org/subfields/2213","display_name":"Safety, Risk, Reliability and Quality"},"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/resilience","display_name":"Resilience (materials science)","score":0.5511531233787537},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5116046071052551},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5042406320571899},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.47176817059516907},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.15286323428153992},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1519797146320343},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.10583502054214478},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.06352341175079346}],"concepts":[{"id":"https://openalex.org/C2779585090","wikidata":"https://www.wikidata.org/wiki/Q3457762","display_name":"Resilience (materials science)","level":2,"score":0.5511531233787537},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5116046071052551},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5042406320571899},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.47176817059516907},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.15286323428153992},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1519797146320343},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.10583502054214478},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.06352341175079346},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ojcs.2024.3400696","is_oa":true,"landing_page_url":"https://doi.org/10.1109/ojcs.2024.3400696","pdf_url":"https://ieeexplore.ieee.org/ielx7/8782664/9024218/10530530.pdf","source":{"id":"https://openalex.org/S4210176459","display_name":"IEEE Open Journal of the Computer Society","issn_l":"2644-1268","issn":["2644-1268"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Open Journal of the Computer Society","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:5f60bf2542ee447a9e32adc975dae5f5","is_oa":true,"landing_page_url":"https://doaj.org/article/5f60bf2542ee447a9e32adc975dae5f5","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Open Journal of the Computer Society, Vol 6, Pp 85-96 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/ojcs.2024.3400696","is_oa":true,"landing_page_url":"https://doi.org/10.1109/ojcs.2024.3400696","pdf_url":"https://ieeexplore.ieee.org/ielx7/8782664/9024218/10530530.pdf","source":{"id":"https://openalex.org/S4210176459","display_name":"IEEE Open Journal of the Computer Society","issn_l":"2644-1268","issn":["2644-1268"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Open Journal of the Computer Society","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4396910092.pdf"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W2021337678","https://openalex.org/W2083613288","https://openalex.org/W2108598243","https://openalex.org/W2152211247","https://openalex.org/W2767260595","https://openalex.org/W2903175372","https://openalex.org/W2946682676","https://openalex.org/W3002446690","https://openalex.org/W3013682536","https://openalex.org/W3034721499","https://openalex.org/W3034900101","https://openalex.org/W3094502228","https://openalex.org/W3114323021","https://openalex.org/W3131518417","https://openalex.org/W3134352527","https://openalex.org/W3135074210","https://openalex.org/W3138516171","https://openalex.org/W3170874841","https://openalex.org/W3177318507","https://openalex.org/W3187862527","https://openalex.org/W3188924112","https://openalex.org/W3189398641","https://openalex.org/W3196974791","https://openalex.org/W3205743929","https://openalex.org/W3208251394","https://openalex.org/W4206706211","https://openalex.org/W4211189626","https://openalex.org/W4281606577","https://openalex.org/W4287822963","https://openalex.org/W4287882613","https://openalex.org/W4295312788","https://openalex.org/W4309490745","https://openalex.org/W4312295823","https://openalex.org/W4312358791","https://openalex.org/W4312366852","https://openalex.org/W4384026312","https://openalex.org/W4385245566","https://openalex.org/W4386212580","https://openalex.org/W4386214823","https://openalex.org/W4387321084","https://openalex.org/W4388662247","https://openalex.org/W4404615757","https://openalex.org/W6745889759","https://openalex.org/W6766978945","https://openalex.org/W6784333009","https://openalex.org/W6788135285"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2051487156","https://openalex.org/W2073681303","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Vision":[0],"Transformers":[1],"are":[2],"being":[3],"increasingly":[4],"deployed":[5],"in":[6,20,121,149,179],"safety-critical":[7],"applications":[8],"that":[9,40,125,134,147],"demand":[10],"high":[11,90,96],"reliability.":[12],"Ensuring":[13],"the":[14,25,64,71,85,113,122,174],"correct":[15],"execution":[16],"of":[17,50,60,66,74,84,176,201],"these":[18],"models":[19,124],"GPUs":[21],"is":[22],"critical,":[23],"despite":[24],"potential":[26],"for":[27,141,194],"transient":[28],"hardware":[29],"errors.":[30],"We":[31,98,188],"propose":[32],"a":[33,82,104,150],"novel":[34],"algorithm-based":[35],"resilience":[36,46,65],"framework":[37,178],"called":[38],"ALBERTA":[39],"allows":[41],"us":[42],"to":[43,70,81],"perform":[44],"end-to-end":[45],"analysis":[47],"and":[48,62,159,167],"protection":[49],"transformer-based":[51],"architectures.":[52],"First,":[53],"our":[54,135,177],"work":[55],"develops":[56],"an":[57,190,199],"efficient":[58,191],"process":[59],"computing":[61],"ranking":[63],"transformers":[67],"layers.":[68],"Due":[69],"large":[72],"size":[73],"transformer":[75,123],"models,":[76],"applying":[77],"traditional":[78],"network":[79],"redundancy":[80],"subset":[83],"most":[86,114],"vulnerable":[87,115],"layers":[88,120],"provides":[89],"error":[91,107],"coverage":[92,140],"albeit":[93],"with":[94,152,198],"impractically":[95],"overhead.":[97],"address":[99],"this":[100],"shortcoming":[101],"by":[102],"providing":[103],"software-directed,":[105],"checksum-based":[106],"detection":[108,197],"technique":[109],"aimed":[110],"at":[111],"protecting":[112],"general":[116],"matrix":[117],"multiply":[118],"(GEMM)":[119],"use":[126],"either":[127],"floating-point":[128],"or":[129],"integer":[130],"arithmetic.":[131],"Results":[132],"show":[133],"approach":[136],"achieves":[137],"over":[138],"99%":[139],"errors":[142],"(single":[143],"bit-flip":[144],"fault":[145],"model)":[146],"result":[148],"mismatch":[151],"<inline-formula":[153,160],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[154,161],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[155,162],"notation=\"LaTeX\">$&lt;":[156,163],"$</tex-math></inline-formula>":[157,164],"0.2%":[158],"0.01%":[165],"computation":[166],"memory":[168],"overheads,":[169],"respectively.":[170],"Lastly,":[171],"we":[172],"present":[173],"applicability":[175],"various":[180],"modern":[181],"GPU":[182],"architectures":[183],"under":[184],"different":[185],"numerical":[186],"precisions.":[187],"introduce":[189],"self-correction":[192],"mechanism":[193],"resolving":[195],"erroneous":[196],"average":[200],"less":[202],"than":[203],"2%":[204],"overhead":[205],"per":[206],"error.":[207]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3}],"updated_date":"2026-03-13T16:22:10.518609","created_date":"2025-10-10T00:00:00"}
