{"id":"https://openalex.org/W4408847328","doi":"https://doi.org/10.1145/3689031.3696088","title":"FlowCheck: Decoupling Checkpointing and Training of Large-Scale Models","display_name":"FlowCheck: Decoupling Checkpointing and Training of Large-Scale Models","publication_year":2025,"publication_date":"2025-03-26","ids":{"openalex":"https://openalex.org/W4408847328","doi":"https://doi.org/10.1145/3689031.3696088"},"language":"en","primary_location":{"id":"doi:10.1145/3689031.3696088","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3689031.3696088","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twentieth European Conference on Computer Systems","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/A5029231567","display_name":"Zimeng Huang","orcid":"https://orcid.org/0000-0002-5016-8472"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zimeng Huang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China and Alibaba Cloud Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China and Alibaba Cloud Hangzhou, China","institution_ids":["https://openalex.org/I45928872","https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066328795","display_name":"Hao Nie","orcid":"https://orcid.org/0000-0002-3031-5930"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Nie","raw_affiliation_strings":["Alibaba Cloud, Hangzhou, China and Peking University Beijing, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Cloud, Hangzhou, China and Peking University Beijing, China","institution_ids":["https://openalex.org/I45928872","https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114173385","display_name":"Haonan Jia","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haonan Jia","raw_affiliation_strings":["Alibaba Cloud, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Cloud, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100669526","display_name":"Bo Jiang","orcid":"https://orcid.org/0000-0001-6711-4342"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Jiang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000249216","display_name":"Junchen Guo","orcid":"https://orcid.org/0000-0002-9018-8881"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junchen Guo","raw_affiliation_strings":["Alibaba Cloud, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Cloud, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100737655","display_name":"Jianyuan Lu","orcid":"https://orcid.org/0000-0003-2502-8686"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianyuan Lu","raw_affiliation_strings":["Alibaba Cloud, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Cloud, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038604516","display_name":"Rong Wen","orcid":"https://orcid.org/0009-0003-6384-1165"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rong Wen","raw_affiliation_strings":["Alibaba Cloud, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Cloud, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091295237","display_name":"Biao Lyu","orcid":"https://orcid.org/0000-0002-8096-5528"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Biao Lyu","raw_affiliation_strings":["Zhejiang University, Hangzhou, China and Alibaba Cloud Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China and Alibaba Cloud Hangzhou, China","institution_ids":["https://openalex.org/I45928872","https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078546063","display_name":"Shunmin Zhu","orcid":"https://orcid.org/0000-0001-7756-0952"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shunmin Zhu","raw_affiliation_strings":["Hangzhou Feitian Cloud Hangzhou, China and Alibaba Cloud Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Hangzhou Feitian Cloud Hangzhou, China and Alibaba Cloud Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034483183","display_name":"Xinbing Wang","orcid":"https://orcid.org/0000-0002-0357-8356"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinbing Wang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5029231567"],"corresponding_institution_ids":["https://openalex.org/I183067930","https://openalex.org/I45928872"],"apc_list":null,"apc_paid":null,"fwci":1.4196,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.80312609,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1334","last_page":"1349"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9990000128746033,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9990000128746033,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9965999722480774,"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/decoupling","display_name":"Decoupling (probability)","score":0.8055211901664734},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7623934745788574},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.7153998613357544},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.6110309362411499},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3794543147087097},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3229812681674957},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.11423066258430481},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07436108589172363},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.0546545684337616},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.05048888921737671}],"concepts":[{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.8055211901664734},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7623934745788574},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.7153998613357544},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.6110309362411499},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3794543147087097},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3229812681674957},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.11423066258430481},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07436108589172363},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0546545684337616},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.05048888921737671},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3689031.3696088","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3689031.3696088","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twentieth European Conference on Computer Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4880947309","display_name":null,"funder_award_id":"62072302,61960206002","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W95608104","https://openalex.org/W2126210439","https://openalex.org/W2731948420","https://openalex.org/W2734941459","https://openalex.org/W2969388332","https://openalex.org/W2995257931","https://openalex.org/W3013227474","https://openalex.org/W3089731223","https://openalex.org/W3129831491","https://openalex.org/W3132107458","https://openalex.org/W3137114593","https://openalex.org/W3204998121","https://openalex.org/W4224308101","https://openalex.org/W4280576269","https://openalex.org/W4297882618","https://openalex.org/W4321446170","https://openalex.org/W4372267133","https://openalex.org/W4381886086","https://openalex.org/W4386117806","https://openalex.org/W4386768656","https://openalex.org/W4387302750","https://openalex.org/W4388031315","https://openalex.org/W4391983842","https://openalex.org/W4392825446","https://openalex.org/W4393145114","https://openalex.org/W6810081322"],"related_works":["https://openalex.org/W4313561376","https://openalex.org/W3103825105","https://openalex.org/W230091440","https://openalex.org/W3027880158","https://openalex.org/W3207533102","https://openalex.org/W1617565119","https://openalex.org/W160381218","https://openalex.org/W2512958550","https://openalex.org/W2004102934","https://openalex.org/W4366455350"],"abstract_inverted_index":{"Checkpointing":[0],"is":[1,133],"becoming":[2],"a":[3,52,90],"hotspot":[4],"of":[5,44,85,120],"interest":[6],"in":[7],"both":[8],"academia":[9],"and":[10,118,153,170,177,190],"industry":[11],"as":[12],"the":[13,29,42,61,69,74,82,127,130,166,172],"primary":[14],"fault-tolerance":[15],"method":[16],"for":[17,101],"large":[18],"model":[19],"training.":[20,70,87],"However,":[21],"existing":[22,167],"checkpoint":[23,58,65,183],"designs":[24],"are":[25],"tightly":[26],"coupled":[27],"with":[28,185],"training":[30,38,62,124,168,198],"process,":[31,63],"leading":[32],"to":[33,93,108,114,136,139],"interruptions":[34],"that":[35,56,180,192],"reduce":[36,41],"overall":[37],"efficiency.":[39],"To":[40,97],"impact":[43,187],"checkpoints":[45,75],"on":[46,129,188],"training,":[47,189],"this":[48,95],"paper":[49],"presents":[50],"FlowCheck,":[51],"novel":[53],"checkpointing":[54,102,163],"system":[55,164],"decouples":[57],"operations":[59,184],"from":[60,81,123],"enabling":[64],"saving":[66],"without":[67],"blocking":[68],"Specifically,":[71],"FlowCheck":[72,88,159,181,193],"updates":[73],"by":[76],"extracting":[77],"complete":[78],"gradient":[79,121],"information":[80],"network":[83,92,169],"traffic":[84,100,151],"normal":[86],"deploys":[89],"traffic-mirroring":[91],"support":[94],"design.":[96],"utilize":[98],"mirrored":[99],"operations,":[103],"two":[104,146,174],"key":[105,147],"challenges":[106],"need":[107,113],"be":[109],"addressed.":[110],"First,":[111],"we":[112],"achieve":[115],"precise":[116],"identification":[117],"extraction":[119],"packets":[122],"traffic.":[125],"Second,":[126],"transmission":[128],"mirror":[131],"link":[132],"unreliable":[134],"due":[135],"its":[137],"inability":[138],"trigger":[140],"retransmission":[141],"upon":[142],"packet":[143,155],"loss.":[144],"Through":[145],"designs:":[148],"(1)":[149],"packet-counting-based":[150],"identification,":[152],"(2)":[154],"redundancy":[156],"recovery":[157],"mechanism,":[158],"implements":[160],"an":[161],"efficient":[162],"using":[165],"solves":[171],"above":[173],"challenges.":[175],"Experiments":[176],"estimations":[178],"verify":[179],"achieves":[182,194],"zero":[186],"demonstrate":[191],"over":[195],"98%":[196],"effective":[197],"time":[199],"under":[200],"practical":[201],"fault":[202],"conditions.":[203]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}
