{"id":"https://openalex.org/W4321446170","doi":"https://doi.org/10.1145/3572848.3577510","title":"Swift","display_name":"Swift","publication_year":2023,"publication_date":"2023-02-21","ids":{"openalex":"https://openalex.org/W4321446170","doi":"https://doi.org/10.1145/3572848.3577510"},"language":"en","primary_location":{"id":"doi:10.1145/3572848.3577510","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3572848.3577510","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming","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/A5030911554","display_name":"Yuchen Zhong","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Yuchen Zhong","raw_affiliation_strings":["The University of Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"The University of Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020661868","display_name":"Guangming Sheng","orcid":"https://orcid.org/0000-0003-3395-3994"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Guangming Sheng","raw_affiliation_strings":["The University of Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"The University of Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101415161","display_name":"Juncheng Liu","orcid":"https://orcid.org/0000-0002-5895-0581"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Juncheng Liu","raw_affiliation_strings":["OneFlow Inc., China"],"affiliations":[{"raw_affiliation_string":"OneFlow Inc., China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036378701","display_name":"Jinhui Yuan","orcid":"https://orcid.org/0000-0003-1410-7792"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinhui Yuan","raw_affiliation_strings":["OneFlow Inc., China"],"affiliations":[{"raw_affiliation_string":"OneFlow Inc., China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012597518","display_name":"Chuan Wu","orcid":"https://orcid.org/0000-0002-3144-4398"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Chuan Wu","raw_affiliation_strings":["The University of Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"The University of Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5030911554"],"corresponding_institution_ids":["https://openalex.org/I889458895"],"apc_list":null,"apc_paid":null,"fwci":0.3777,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.57051848,"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":"447","last_page":"449"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9997000098228455,"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":0.9997000098228455,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","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"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9954000115394592,"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":0.8167414665222168},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6944267153739929},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.6852171421051025},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.5961992144584656},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5839363932609558},{"id":"https://openalex.org/keywords/swift","display_name":"Swift","score":0.5659232139587402},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5421338081359863},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3524971306324005},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3305102586746216},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1704343557357788},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.12484660744667053},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.08627340197563171},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.06982558965682983}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8167414665222168},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6944267153739929},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.6852171421051025},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.5961992144584656},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5839363932609558},{"id":"https://openalex.org/C116188536","wikidata":"https://www.wikidata.org/wiki/Q17118377","display_name":"Swift","level":2,"score":0.5659232139587402},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5421338081359863},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3524971306324005},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3305102586746216},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1704343557357788},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.12484660744667053},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.08627340197563171},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06982558965682983},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3572848.3577510","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3572848.3577510","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6200000047683716,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W2117539524","https://openalex.org/W2912574597","https://openalex.org/W2963748441"],"related_works":["https://openalex.org/W3198734187","https://openalex.org/W2078379271","https://openalex.org/W2043460294","https://openalex.org/W4210712718","https://openalex.org/W1905398909","https://openalex.org/W1862835629","https://openalex.org/W2099111379","https://openalex.org/W2136799148","https://openalex.org/W2897533804","https://openalex.org/W2890506991"],"abstract_inverted_index":{"As":[0],"the":[1,37,71,89,94,97,102,108,132,136,148],"size":[2],"of":[3,36,83,88,96,107],"deep":[4,64],"learning":[5],"models":[6,47],"gets":[7],"larger":[8],"and":[9,15,27,48,79,104,130,152],"larger,":[10],"training":[11,67,77,157],"takes":[12],"longer":[13],"time":[14,151],"more":[16],"resources,":[17],"making":[18,84],"fault":[19],"tolerance":[20],"critical.":[21],"Existing":[22],"state-of-the-art":[23,164],"methods":[24,165],"like":[25],"Check-Freq":[26],"Elastic":[28],"Horovod":[29],"need":[30],"to":[31,50,134,163],"back":[32],"up":[33],"a":[34,57,119,140],"copy":[35,87],"model":[38,80,90,98,109,169],"state":[39,99,110,138],"in":[40,111],"memory,":[41],"which":[42,126],"is":[43],"costly":[44],"for":[45,62,114],"large":[46],"leads":[49],"non-trivial":[51],"overhead.":[52],"This":[53],"paper":[54],"presents":[55],"Swift,":[56],"novel":[58],"failure":[59,72,103,115,149],"recovery":[60,73,150],"design":[61],"distributed":[63],"neural":[65],"network":[66],"that":[68,144],"significantly":[69,146],"reduces":[70,147],"overhead":[74],"without":[75,166],"affecting":[76],"throughput":[78,158],"accuracy.":[81,170],"Instead":[82],"an":[85],"additional":[86],"state,":[91],"Swift":[92,145],"resolves":[93],"inconsistencies":[95],"caused":[100],"by":[101],"exploits":[105],"replicas":[106,123],"data":[112,129],"parallelism":[113],"recovery.":[116],"We":[117],"propose":[118],"logging-based":[120],"approach":[121],"when":[122],"are":[124],"unavailable,":[125],"records":[127],"intermediate":[128],"replays":[131],"computation":[133],"recover":[135],"lost":[137],"upon":[139],"failure.":[141],"Evaluations":[142],"show":[143],"achieves":[153],"similar":[154],"or":[155],"better":[156],"during":[159],"failure-free":[160],"execution":[161],"compared":[162],"degrading":[167],"final":[168]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2023-02-22T00:00:00"}