{"id":"https://openalex.org/W4405306354","doi":"https://doi.org/10.1109/nas63802.2024.10781359","title":"TranLogs: Lossless Failure Recovery Empowered by Training Logs","display_name":"TranLogs: Lossless Failure Recovery Empowered by Training Logs","publication_year":2024,"publication_date":"2024-11-09","ids":{"openalex":"https://openalex.org/W4405306354","doi":"https://doi.org/10.1109/nas63802.2024.10781359"},"language":"en","primary_location":{"id":"doi:10.1109/nas63802.2024.10781359","is_oa":false,"landing_page_url":"https://doi.org/10.1109/nas63802.2024.10781359","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Networking, Architecture and Storage (NAS)","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/A5115596088","display_name":"Xiaoyu Liu","orcid":"https://orcid.org/0009-0004-2165-0210"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaoyu Liu","raw_affiliation_strings":["Zhejiang Lab,HangZhou,China"],"affiliations":[{"raw_affiliation_string":"Zhejiang Lab,HangZhou,China","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036840192","display_name":"Lingfang Zeng","orcid":"https://orcid.org/0000-0003-3130-3015"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingfang Zeng","raw_affiliation_strings":["Zhejiang Lab,HangZhou,China"],"affiliations":[{"raw_affiliation_string":"Zhejiang Lab,HangZhou,China","institution_ids":["https://openalex.org/I4210123185"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5115596088"],"corresponding_institution_ids":["https://openalex.org/I4210123185"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.25228758,"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":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":0.04639999940991402,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.04639999940991402,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/lossless-compression","display_name":"Lossless compression","score":0.7401316165924072},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6577922105789185},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5841004252433777},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.35750246047973633},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.17302468419075012},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.14175668358802795},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13441693782806396}],"concepts":[{"id":"https://openalex.org/C81081738","wikidata":"https://www.wikidata.org/wiki/Q55542","display_name":"Lossless compression","level":3,"score":0.7401316165924072},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6577922105789185},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5841004252433777},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.35750246047973633},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.17302468419075012},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.14175668358802795},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13441693782806396},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/nas63802.2024.10781359","is_oa":false,"landing_page_url":"https://doi.org/10.1109/nas63802.2024.10781359","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Networking, Architecture and Storage (NAS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Climate action","id":"https://metadata.un.org/sdg/13","score":0.5099999904632568}],"awards":[{"id":"https://openalex.org/G6435396388","display_name":null,"funder_award_id":"2022YFB4500405","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G8000429783","display_name":null,"funder_award_id":"U22A6001","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2047196223","https://openalex.org/W2125621954","https://openalex.org/W2897882964","https://openalex.org/W2903011884","https://openalex.org/W2953419262","https://openalex.org/W2954948187","https://openalex.org/W2964382283","https://openalex.org/W2969688067","https://openalex.org/W3008109267","https://openalex.org/W3016478929","https://openalex.org/W3021124033","https://openalex.org/W3031953854","https://openalex.org/W3031954582","https://openalex.org/W3043941844","https://openalex.org/W3045102472","https://openalex.org/W3193638860","https://openalex.org/W3195997474","https://openalex.org/W4244777963","https://openalex.org/W4360995100","https://openalex.org/W4386117806","https://openalex.org/W4387302750","https://openalex.org/W4390097689","https://openalex.org/W4394923484"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W3106969033","https://openalex.org/W2186939576","https://openalex.org/W2357988910","https://openalex.org/W2948148442","https://openalex.org/W2377158164","https://openalex.org/W2187600494","https://openalex.org/W2114030128"],"abstract_inverted_index":{"When":[0],"running":[1],"deep":[2,94,124],"learning":[3,95,125],"training":[4,10,28,66,96,116,123,144,192,206],"jobs,":[5],"in":[6,30,57,156,163,184],"order":[7],"to":[8,13,22,33,48,77,85,129,132,198],"prevent":[9],"loss":[11,89,166,186],"due":[12],"softwarelhardware":[14],"failures,":[15,161],"a":[16,109,164],"checkpointing":[17,50,100],"mechanism":[18],"is":[19,45,90,153,196],"usually":[20],"used":[21],"periodically":[23],"store":[24],"snapshots":[25],"of":[26,42,65,142,189,210],"the":[27,39,49,53,58,75,134,139,147,150,185,190,199,204,208],"model":[29,73,81,87,143,160,205],"non-volatile":[31],"memory":[32],"facilitate":[34],"recovery":[35,40,83,104,112,121],"from":[36],"failures.":[37],"However,":[38],"effect":[41],"this":[43],"method":[44,113],"closely":[46],"related":[47],"period":[51,64],"and":[52,56,137,158,181,187],"failure":[54,111,120],"time,":[55],"worst":[59],"case,":[60],"even":[61],"nearly":[62],"one":[63],"accuracy":[67,188],"will":[68],"be":[69],"lost.":[70],"With":[71],"increasing":[72],"sizes,":[74],"need":[76],"develop":[78],"more":[79,91],"fine-grained":[80],"fault":[82,88,103],"methods":[84],"reduce":[86],"urgent":[92],"for":[93,118],"tasks":[97],"that":[98],"use":[99,130],"mechanisms":[101],"as":[102],"guarantees.":[105],"We":[106],"present":[107],"TranLogs,":[108],"checkpoint":[110,135,151],"combined":[114],"with":[115],"logs":[117],"lossless":[119],"when":[122],"models.":[126],"TranLogs":[127,169],"proposes":[128],"logging":[131],"supplement":[133],"file":[136,152],"track":[138],"iterative":[140],"process":[141],"parameters.":[145],"For":[146],"situation":[148],"where":[149],"not":[154],"updated":[155],"time":[157],"encounters":[159],"resulting":[162],"large":[165],"during":[167],"recovery,":[168],"can":[170],"handle":[171],"it":[172],"effectively.":[173],"The":[174],"best-case":[175],"scenario":[176],"achieves":[177],"about":[178],"24":[179],"%":[180],"6%":[182],"improvement":[183],"recovered":[191],"state,":[193],"respectively,":[194],"which":[195],"closer":[197],"state":[200],"already":[201],"achieved":[202],"by":[203],"at":[207],"moment":[209],"failure.":[211]},"counts_by_year":[],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}