{"id":"https://openalex.org/W3129341457","doi":"https://doi.org/10.1109/tpds.2021.3059420","title":"A Fault-Tolerant Distributed Framework for Asynchronous Iterative Computations","display_name":"A Fault-Tolerant Distributed Framework for Asynchronous Iterative Computations","publication_year":2021,"publication_date":"2021-02-15","ids":{"openalex":"https://openalex.org/W3129341457","doi":"https://doi.org/10.1109/tpds.2021.3059420","mag":"3129341457"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2021.3059420","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2021.3059420","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"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 Transactions on Parallel and Distributed Systems","raw_type":"journal-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/A5021333364","display_name":"Tian Zhou","orcid":"https://orcid.org/0000-0002-1473-9960"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]},{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Tian Zhou","raw_affiliation_strings":["Department of Computer Science and Technology, Xi'an Jiaotong University, Xi'an, China","Department of Electrical and Computer Engineering, University of Massachusetts Amhers, Amherst, MA, USA"],"raw_orcid":"https://orcid.org/0000-0002-1473-9960","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Massachusetts Amhers, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019000951","display_name":"Lixin Gao","orcid":"https://orcid.org/0000-0002-9017-5132"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lixin Gao","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Massachusetts Amhers, Amherst, MA, USA"],"raw_orcid":"https://orcid.org/0000-0002-9017-5132","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Massachusetts Amhers, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075845093","display_name":"Xiaohong Guan","orcid":"https://orcid.org/0000-0002-8826-0362"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaohong Guan","raw_affiliation_strings":["Systems Engineering Instituteg, Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Systems Engineering Instituteg, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5197,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.66229551,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"32","issue":"8","first_page":"2062","last_page":"2073"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9988999962806702,"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"}},"topics":[{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9988999962806702,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9987999796867371,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9979000091552734,"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/asynchronous-communication","display_name":"Asynchronous communication","score":0.9014357328414917},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8875598907470703},{"id":"https://openalex.org/keywords/snapshot","display_name":"Snapshot (computer storage)","score":0.8713809847831726},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.6757692098617554},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6122066378593445},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5173293948173523},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.4490084946155548},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.43314534425735474},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.34710991382598877},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3393350839614868},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.31229811906814575},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.21050086617469788},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.19187983870506287}],"concepts":[{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.9014357328414917},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8875598907470703},{"id":"https://openalex.org/C55282118","wikidata":"https://www.wikidata.org/wiki/Q252683","display_name":"Snapshot (computer storage)","level":2,"score":0.8713809847831726},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.6757692098617554},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6122066378593445},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5173293948173523},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.4490084946155548},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.43314534425735474},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.34710991382598877},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3393350839614868},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.31229811906814575},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.21050086617469788},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.19187983870506287},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2021.3059420","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2021.3059420","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"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 Transactions on Parallel and Distributed Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5899999737739563,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[{"id":"https://openalex.org/G2022019916","display_name":null,"funder_award_id":"CNS-1815412","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2670886962","display_name":null,"funder_award_id":"CNS-1908536","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W78077100","https://openalex.org/W200298483","https://openalex.org/W1913482755","https://openalex.org/W2008729472","https://openalex.org/W2013344760","https://openalex.org/W2016924386","https://openalex.org/W2035176107","https://openalex.org/W2036631599","https://openalex.org/W2043494924","https://openalex.org/W2045271686","https://openalex.org/W2086247510","https://openalex.org/W2096544401","https://openalex.org/W2100830825","https://openalex.org/W2119738171","https://openalex.org/W2120458882","https://openalex.org/W2121966774","https://openalex.org/W2131053137","https://openalex.org/W2131975293","https://openalex.org/W2141711298","https://openalex.org/W2170616854","https://openalex.org/W2173213060","https://openalex.org/W2189465200","https://openalex.org/W2266486761","https://openalex.org/W2435174210","https://openalex.org/W2521836998","https://openalex.org/W2792839583","https://openalex.org/W4239429564","https://openalex.org/W6603201521","https://openalex.org/W6607964021","https://openalex.org/W6679815717","https://openalex.org/W6687322159"],"related_works":["https://openalex.org/W2542847180","https://openalex.org/W2116677773","https://openalex.org/W3034994054","https://openalex.org/W2155226960","https://openalex.org/W2805712290","https://openalex.org/W2909129499","https://openalex.org/W2761598930","https://openalex.org/W2392087771","https://openalex.org/W2155261584","https://openalex.org/W2553994394"],"abstract_inverted_index":{"Asynchronous":[0],"iterative":[1,54],"computations":[2,55],"(AIC)":[3],"are":[4],"common":[5],"in":[6,19],"machine":[7],"learning":[8],"and":[9,100],"data":[10],"mining":[11],"systems.":[12],"However,":[13],"the":[14,64,69,77,85,107,119,136,150],"lack":[15],"of":[16,63,71,110,152],"synchronization":[17,35],"barriers":[18],"asynchronous":[20,53,131],"processing":[21,26],"brings":[22],"challenges":[23],"for":[24,52],"continuous":[25],"while":[27],"workers":[28,39],"might":[29],"fail.":[30],"There":[31],"is":[32,112,124],"no":[33],"global":[34],"point":[36],"that":[37,76,106,146],"all":[38],"can":[40,83],"roll":[41],"back":[42],"to.":[43],"In":[44],"this":[45],"article,":[46],"we":[47],"propose":[48],"a":[49,60,142],"fault-tolerant":[50],"framework":[51,58,93],"(FAIC).":[56],"Our":[57,102,139],"takes":[59],"virtual":[61,78],"snapshot":[62,79,132],"AIC":[65,86,97],"system":[66,87],"without":[67],"halting":[68],"computation":[70],"any":[72],"worker.":[73],"We":[74,89],"prove":[75],"capture":[80],"by":[81],"FAIC":[82,92,111,123,147],"recover":[84],"correctly.":[88],"evaluate":[90],"our":[91],"on":[94,141],"two":[95],"existing":[96],"systems,":[98],"Maiter":[99],"NOMAD.":[101],"experiment":[103],"result":[104],"shows":[105],"checkpoint":[108,121],"overhead":[109],"more":[113],"than":[114,118,129],"50":[115],"percent":[116,127],"shorter":[117],"synchronous":[120],"method.":[122],"around":[125],"10":[126],"faster":[128],"other":[130],"algorithms,":[133],"such":[134],"as":[135],"Chandy-Lamport":[137],"algorithm.":[138],"experiments":[140],"large":[143],"cluster":[144],"demonstrate":[145],"scales":[148],"with":[149],"number":[151],"workers.":[153]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-21T08:15:58.654021","created_date":"2025-10-10T00:00:00"}