{"id":"https://openalex.org/W3093394987","doi":null,"title":"Check-N-Run: A Checkpointing System for Training Recommendation Models.","display_name":"Check-N-Run: A Checkpointing System for Training Recommendation Models.","publication_year":2020,"publication_date":"2020-10-17","ids":{"openalex":"https://openalex.org/W3093394987","mag":"3093394987"},"language":"en","primary_location":{"id":"mag:3093394987","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2010.08679","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2010.08679","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029184375","display_name":"Assaf Eisenman","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Assaf Eisenman","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011731495","display_name":"Kiran Kumar Matam","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kiran Kumar Matam","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026894469","display_name":"Steven Ingram","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Steven Ingram","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066366329","display_name":"Dheevatsa Mudigere","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dheevatsa Mudigere","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039488725","display_name":"Raghuraman Krishnamoorthi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Raghuraman Krishnamoorthi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018033573","display_name":"Murali Annavaram","orcid":"https://orcid.org/0000-0002-4633-6867","observed_orcids":["https://orcid.org/0000-0002-4633-6867"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Murali Annavaram","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-4633-6867","affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Krishnakumar Nair","orcid":"https://orcid.org/0000-0003-1352-9467","observed_orcids":["https://orcid.org/0000-0003-1352-9467"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Krishnakumar Nair","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-1352-9467","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5090820641","display_name":"Misha Smelyanskiy","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Misha Smelyanskiy","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.46560001373291016,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.46560001373291016,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.26930001378059387,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.13459999859333038,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/checkpointing","display_name":"checkpointing","score":0.9559999704360962},{"id":"https://openalex.org/keywords/recommender-systems","display_name":"recommender systems","score":0.6949999928474426},{"id":"https://openalex.org/keywords/incremental-checkpointing","display_name":"incremental checkpointing","score":0.9150000214576721},{"id":"https://openalex.org/keywords/model-quantization","display_name":"model quantization","score":0.8069999814033508},{"id":"https://openalex.org/keywords/online-training","display_name":"online training","score":0.7129999995231628},{"id":"https://openalex.org/keywords/fault-recovery","display_name":"fault recovery","score":0.8809999823570251},{"id":"https://openalex.org/keywords/large-scale-model-training","display_name":"large-scale model training","score":0.5040000081062317}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8517218232154846},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.8092618584632874},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6559498906135559},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.622780442237854},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.48127979040145874},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.42791610956192017},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.25734493136405945},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2482881247997284},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.22764098644256592},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"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":"mag:3093394987","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2010.08679","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:3093394987","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2010.08679","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W39269388","https://openalex.org/W1442374986","https://openalex.org/W2035492130","https://openalex.org/W2131053137","https://openalex.org/W2132914442","https://openalex.org/W2161537327","https://openalex.org/W2165698076","https://openalex.org/W2286365479","https://openalex.org/W2336650964","https://openalex.org/W2407022425","https://openalex.org/W2512971201","https://openalex.org/W2563343794","https://openalex.org/W2884150179","https://openalex.org/W2900810680","https://openalex.org/W2982479999","https://openalex.org/W2984020950","https://openalex.org/W3016842236","https://openalex.org/W3021124033"],"related_works":["https://openalex.org/W3158296418","https://openalex.org/W4410543986","https://openalex.org/W4400233507","https://openalex.org/W4414244616","https://openalex.org/W4386117806","https://openalex.org/W3150866682","https://openalex.org/W4406157447","https://openalex.org/W6891424356","https://openalex.org/W3095994716","https://openalex.org/W4385585472"],"abstract_inverted_index":{"Checkpoints":[0,34],"play":[1],"an":[2],"important":[3,13],"role":[4],"in":[5],"training":[6,24,28,80,124],"recommendation":[7,48,82],"systems":[8],"at":[9,147],"scale.":[10],"They":[11],"are":[12,35],"for":[14,79],"many":[15],"use":[16],"cases,":[17],"including":[18],"failure":[19],"recovery":[20],"to":[21,29,38,89,116,130],"ensure":[22],"rapid":[23],"progress,":[25],"and":[26,46,54,64,100,138,149],"online":[27],"improve":[30,152],"inference":[31],"prediction":[32],"accuracy.":[33,125],"typically":[36,44],"written":[37],"remote,":[39],"persistent":[40],"storage.":[41],"Given":[42],"the":[43,51,60,69,102,106,119,132,139,157],"large":[45,81],"ever-increasing":[47],"model":[49],"sizes,":[50],"checkpoint":[52,120,153],"frequency":[53],"effectiveness":[55],"is":[56],"often":[57],"bottlenecked":[58],"by":[59,136,142],"storage":[61],"write":[62,134],"bandwidth":[63,135],"capacity,":[65],"as":[66,68],"well":[67],"network":[70],"bandwidth.":[71],"We":[72],"present":[73],"Check-N-Run,":[74],"a":[75],"scalable":[76],"checkpointing":[77],"system":[78],"models.":[83],"Check-N-Run":[84,129],"uses":[85],"two":[86],"primary":[87],"approaches":[88],"address":[90],"these":[91],"challenges.":[92],"First,":[93],"it":[94,112],"applies":[95],"incremental":[96],"checkpointing,":[97],"which":[98],"tracks":[99],"checkpoints":[101],"modified":[103],"part":[104],"of":[105,110,160],"model.":[107],"On":[108],"top":[109],"that,":[111],"leverages":[113],"quantization":[114],"techniques":[115,127],"significantly":[117,151],"reduce":[118,131],"size,":[121],"without":[122],"degrading":[123],"These":[126],"allow":[128],"required":[133,140],"6-17x":[137],"capacity":[141],"2.5-8x":[143],"on":[144],"real-world":[145],"models":[146],"Facebook,":[148],"thereby":[150],"capabilities":[154],"while":[155],"reducing":[156],"total":[158],"cost":[159],"ownership.":[161]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2020-10-22T00:00:00"}