{"id":"https://openalex.org/W2587322763","doi":"https://doi.org/10.1145/3022227.3022295","title":"A quantitative analysis of fault tolerance mechanisms for parallel machine learning systems with parameter servers","display_name":"A quantitative analysis of fault tolerance mechanisms for parallel machine learning systems with parameter servers","publication_year":2017,"publication_date":"2017-01-05","ids":{"openalex":"https://openalex.org/W2587322763","doi":"https://doi.org/10.1145/3022227.3022295","mag":"2587322763"},"language":"en","primary_location":{"id":"doi:10.1145/3022227.3022295","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3022227.3022295","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th International Conference on Ubiquitous Information Management and Communication","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/A5101470604","display_name":"Mingxi Li","orcid":"https://orcid.org/0000-0003-3987-017X"},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Mingxi Li","raw_affiliation_strings":["University of Tsukuba, Tsukuba, Japan"],"affiliations":[{"raw_affiliation_string":"University of Tsukuba, Tsukuba, Japan","institution_ids":["https://openalex.org/I146399215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108062798","display_name":"Yusuke Tanimura","orcid":"https://orcid.org/0000-0002-9140-7169"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yusuke Tanimura","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology, Tsukuba, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology, Tsukuba, Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027931271","display_name":"Hidemoto Nakada","orcid":"https://orcid.org/0000-0002-8901-2504"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hidemoto Nakada","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology, Tsukuba, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology, Tsukuba, Japan","institution_ids":["https://openalex.org/I73613424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101470604"],"corresponding_institution_ids":["https://openalex.org/I146399215"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01339514,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10715","display_name":"Distributed and Parallel Computing Systems","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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9965000152587891,"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/server","display_name":"Server","score":0.820534884929657},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8103622198104858},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.7985600233078003},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.6988894939422607},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5533520579338074},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5472105145454407},{"id":"https://openalex.org/keywords/software-fault-tolerance","display_name":"Software fault tolerance","score":0.5356478691101074},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47055983543395996},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4237586557865143},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4237102270126343},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.21999579668045044},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2123318314552307}],"concepts":[{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.820534884929657},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8103622198104858},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.7985600233078003},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.6988894939422607},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5533520579338074},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5472105145454407},{"id":"https://openalex.org/C50712370","wikidata":"https://www.wikidata.org/wiki/Q4269346","display_name":"Software fault tolerance","level":3,"score":0.5356478691101074},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47055983543395996},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4237586557865143},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4237102270126343},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.21999579668045044},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2123318314552307}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3022227.3022295","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3022227.3022295","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th International Conference on Ubiquitous Information Management and Communication","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1442374986","https://openalex.org/W1554637430","https://openalex.org/W1661809435","https://openalex.org/W2045271686","https://openalex.org/W2074787299","https://openalex.org/W2083842231","https://openalex.org/W2105039796","https://openalex.org/W2114035455","https://openalex.org/W2119541875","https://openalex.org/W2120480077","https://openalex.org/W2142316272","https://openalex.org/W2168231600","https://openalex.org/W2622558987","https://openalex.org/W2950789693","https://openalex.org/W6684859321"],"related_works":["https://openalex.org/W2153096481","https://openalex.org/W2148616436","https://openalex.org/W2102525122","https://openalex.org/W4245282135","https://openalex.org/W4306316843","https://openalex.org/W2130594209","https://openalex.org/W2036953450","https://openalex.org/W4300955944","https://openalex.org/W2170004886","https://openalex.org/W2527822502"],"abstract_inverted_index":{"Parallel":[0],"computation":[1,50,76],"is":[2,23,42],"essential":[3],"for":[4,14],"machine":[5,21,58,86,105],"learning":[6,22,59,87,106],"systems":[7,51,60,77,107],"that":[8,36,112],"handle":[9],"large":[10,31,48,74],"amount":[11],"of":[12,19,33,73,91,103,143],"data":[13],"training.":[15],"One":[16],"popular":[17],"form":[18],"parallel":[20,85,104,135],"the":[24,70,100,117,123,141,144],"one":[25],"called":[26],"'Data":[27],"parallel'":[28],"which":[29,108],"use":[30,109],"number":[32],"parameter":[34,55,110],"servers":[35,111],"manage":[37],"computational":[38],"workers.":[39],"Fault":[40],"tolerance":[41,72,102,132],"always":[43],"a":[44],"crucial":[45],"issue":[46],"on":[47,69,84],"scale":[49,75],"in":[52,78,89],"general,":[53,79],"and":[54,119,139],"server":[56],"based":[57],"are":[61,66,81],"no":[62,82],"exception.":[63],"However,":[64],"there":[65,80],"many":[67],"discussions":[68,83],"fault":[71,101,131],"systems,":[88],"spite":[90],"their":[92],"unique":[93],"characteristics.":[94],"In":[95],"this":[96],"paper,":[97],"we":[98],"discuss":[99],"provides":[113],"extra":[114],"redundancy":[115],"to":[116],"system":[118],"could":[120],"double":[121],"as":[122],"checkpoint":[124],"server.":[125],"We":[126],"also":[127],"quantitatively":[128],"evaluate":[129],"several":[130],"method":[133],"using":[134],"environment":[136],"simulator":[137],"SimGrid,":[138],"demonstrate":[140],"effectiveness":[142],"proposed":[145],"method.":[146]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
