{"id":"https://openalex.org/W4416199158","doi":"https://doi.org/10.1145/3712285.3759853","title":"FT-Transformer: Resilient and Reliable Transformer with End-to-End Fault Tolerant Attention","display_name":"FT-Transformer: Resilient and Reliable Transformer with End-to-End Fault Tolerant Attention","publication_year":2025,"publication_date":"2025-11-12","ids":{"openalex":"https://openalex.org/W4416199158","doi":"https://doi.org/10.1145/3712285.3759853"},"language":null,"primary_location":{"id":"doi:10.1145/3712285.3759853","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3712285.3759853","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3712285.3759853","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109906601","display_name":"H. L. Dai","orcid":"https://orcid.org/0009-0002-9628-3326"},"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":"Huangliang Dai","raw_affiliation_strings":["University of California, Riverside, Riverside, USA"],"raw_orcid":"https://orcid.org/0009-0002-9628-3326","affiliations":[{"raw_affiliation_string":"University of California, Riverside, Riverside, USA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075806978","display_name":"Shixun Wu","orcid":"https://orcid.org/0000-0001-8637-3307"},"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":"Shixun Wu","raw_affiliation_strings":["University of California, Riverside, Riverside, USA"],"raw_orcid":"https://orcid.org/0000-0001-8637-3307","affiliations":[{"raw_affiliation_string":"University of California, Riverside, Riverside, USA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100779661","display_name":"Jiajun Huang","orcid":"https://orcid.org/0000-0001-5092-3987"},"institutions":[{"id":"https://openalex.org/I2613432","display_name":"University of South Florida","ror":"https://ror.org/032db5x82","country_code":"US","type":"education","lineage":["https://openalex.org/I2613432"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiajun Huang","raw_affiliation_strings":["University of South Florida, Tampa, USA"],"raw_orcid":"https://orcid.org/0000-0001-5092-3987","affiliations":[{"raw_affiliation_string":"University of South Florida, Tampa, USA","institution_ids":["https://openalex.org/I2613432"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071045650","display_name":"Zizhe Jian","orcid":"https://orcid.org/0009-0005-2079-8130"},"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":"Zizhe Jian","raw_affiliation_strings":["University of California, Riverside, Riverside, USA"],"raw_orcid":"https://orcid.org/0009-0005-2079-8130","affiliations":[{"raw_affiliation_string":"University of California, Riverside, Riverside, USA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100513379","display_name":"Yue Zhu","orcid":"https://orcid.org/0009-0009-2273-5618"},"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":"Yue Zhu","raw_affiliation_strings":["University of California, Riverside, Riverside, USA"],"raw_orcid":"https://orcid.org/0009-0009-2273-5618","affiliations":[{"raw_affiliation_string":"University of California, Riverside, Riverside, USA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Haiyang Hu","orcid":"https://orcid.org/0009-0005-8299-6124"},"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":"Haiyang Hu","raw_affiliation_strings":["University of California, Riverside, Riverside, USA"],"raw_orcid":"https://orcid.org/0009-0005-8299-6124","affiliations":[{"raw_affiliation_string":"University of California, Riverside, Riverside, USA","institution_ids":["https://openalex.org/I103635307"]}]},{"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, Riverside, USA"],"raw_orcid":"https://orcid.org/0000-0003-2578-4940","affiliations":[{"raw_affiliation_string":"University of California, Riverside, Riverside, USA","institution_ids":["https://openalex.org/I103635307"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1085","last_page":"1098"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11005","display_name":"Radiation Effects in Electronics","score":0.6685000061988831,"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":0.6685000061988831,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.10790000110864639,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.09070000052452087,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/fault-tolerance","display_name":"Fault tolerance","score":0.7264999747276306},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5277000069618225},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.520799994468689},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.38269999623298645},{"id":"https://openalex.org/keywords/fault-detection-and-isolation","display_name":"Fault detection and isolation","score":0.3382999897003174},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.32030001282691956}],"concepts":[{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.7264999747276306},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.6100000143051147},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6053000092506409},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5277000069618225},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.520799994468689},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.38269999623298645},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.35440000891685486},{"id":"https://openalex.org/C152745839","wikidata":"https://www.wikidata.org/wiki/Q5438153","display_name":"Fault detection and isolation","level":3,"score":0.3382999897003174},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.32030001282691956},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.32019999623298645},{"id":"https://openalex.org/C126953365","wikidata":"https://www.wikidata.org/wiki/Q5438152","display_name":"Fault coverage","level":3,"score":0.3043999969959259},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.2962999939918518},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.29330000281333923},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.28220000863075256},{"id":"https://openalex.org/C167391956","wikidata":"https://www.wikidata.org/wiki/Q1401211","display_name":"Fault model","level":3,"score":0.27649998664855957},{"id":"https://openalex.org/C50712370","wikidata":"https://www.wikidata.org/wiki/Q4269346","display_name":"Software fault tolerance","level":3,"score":0.2644999921321869}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3712285.3759853","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3712285.3759853","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3712285.3759853","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3712285.3759853","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1576341769","https://openalex.org/W1612106836","https://openalex.org/W1979585379","https://openalex.org/W2034593585","https://openalex.org/W2051798865","https://openalex.org/W2061043348","https://openalex.org/W2083613288","https://openalex.org/W2099569658","https://openalex.org/W2125169487","https://openalex.org/W2139318413","https://openalex.org/W2144784023","https://openalex.org/W2145467192","https://openalex.org/W2149431208","https://openalex.org/W2158110624","https://openalex.org/W2318507312","https://openalex.org/W2648669956","https://openalex.org/W2943768976","https://openalex.org/W2945387900","https://openalex.org/W2981743485","https://openalex.org/W3092557781","https://openalex.org/W3096295711","https://openalex.org/W3131922516","https://openalex.org/W3190315974","https://openalex.org/W3206892724","https://openalex.org/W3215256528","https://openalex.org/W4213019189","https://openalex.org/W4252174618","https://openalex.org/W4280513934","https://openalex.org/W4306855837","https://openalex.org/W4376226279","https://openalex.org/W4387008005","https://openalex.org/W4387385773","https://openalex.org/W4404133321","https://openalex.org/W4406610596","https://openalex.org/W4408029605","https://openalex.org/W7084107549"],"related_works":[],"abstract_inverted_index":{"Transformer":[0],"models":[1],"rely":[2],"on":[3],"High-Performance":[4],"Computing":[5],"(HPC)":[6],"resources":[7],"for":[8,30,67],"inference,":[9],"where":[10],"soft":[11],"errors":[12,100],"are":[13,32],"inevitable":[14],"in":[15,49,101],"large-scale":[16],"systems,":[17],"making":[18],"the":[19,22,35,71,74,102],"reliability":[20],"of":[21,98,143],"model":[23],"particularly":[24],"critical.":[25],"Existing":[26],"fault":[27,84,113,126,140],"tolerance":[28,114,127,141],"frameworks":[29],"Transformers":[31,68],"designed":[33],"at":[34],"operation":[36],"level":[37],"without":[38],"architectural":[39],"optimization,":[40],"leading":[41],"to":[42,57,130],"significant":[43],"computational":[44],"and":[45,54,81],"memory":[46],"overhead,":[47],"which":[48],"turn":[50],"reduces":[51],"protection":[52,66,90],"efficiency":[53],"limits":[55],"scalability":[56],"larger":[58],"models.":[59],"In":[60],"this":[61],"paper,":[62],"we":[63,108],"implement":[64],"module-level":[65],"by":[69],"treating":[70],"operations":[72],"within":[73],"attention":[75],"module":[76],"as":[77],"a":[78,110],"single":[79],"kernel":[80],"applying":[82],"end-to-end":[83,125],"tolerance.":[85],"This":[86],"method":[87],"provides":[88],"unified":[89],"across":[91],"multi-step":[92],"computations,":[93],"while":[94],"achieving":[95],"comprehensive":[96],"coverage":[97],"potential":[99],"nonlinear":[103],"computations.":[104],"For":[105],"linear":[106],"modules,":[107],"design":[109],"strided":[111],"algorithm-based":[112],"(ABFT)":[115],"that":[116,123],"avoids":[117],"inter-thread":[118],"communication.":[119],"Experimental":[120],"results":[121],"show":[122],"our":[124],"achieves":[128],"up":[129],"7.56":[131],"\u00d7":[132],"speedup":[133],"over":[134],"traditional":[135],"methods":[136],"with":[137],"an":[138],"average":[139],"overhead":[142],"13.9%.":[144]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-12T00:00:00"}
