{"id":"https://openalex.org/W4414244616","doi":"https://doi.org/10.14778/3750601.3750621","title":"DECK: Experiences on Delta Checkpointing for Industrial Recommendation Systems","display_name":"DECK: Experiences on Delta Checkpointing for Industrial Recommendation Systems","publication_year":2025,"publication_date":"2025-08-01","ids":{"openalex":"https://openalex.org/W4414244616","doi":"https://doi.org/10.14778/3750601.3750621"},"language":"en","primary_location":{"id":"doi:10.14778/3750601.3750621","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3750601.3750621","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","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/A5001847888","display_name":"Xinwen Gao","orcid":"https://orcid.org/0000-0002-2779-7027"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Xin Gao","raw_affiliation_strings":["Meta Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Sibasish Acharya","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sibasish Acharya","raw_affiliation_strings":["Meta Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046913958","display_name":"Sihui Han","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sihui Han","raw_affiliation_strings":["Meta Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041229741","display_name":"Yongxiong Ren","orcid":"https://orcid.org/0000-0002-8291-883X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yongxiong Ren","raw_affiliation_strings":["Meta Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112754141","display_name":"Yanli Zhao","orcid":"https://orcid.org/0000-0002-9231-8360"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanli Zhao","raw_affiliation_strings":["Meta Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101809829","display_name":"Liang Luo","orcid":"https://orcid.org/0000-0003-4222-7986"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang Luo","raw_affiliation_strings":["Meta Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031034355","display_name":"C. W. Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chucheng Wang","raw_affiliation_strings":["Meta Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052938558","display_name":"Pradeep Fernando","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pradeep Fernando","raw_affiliation_strings":["Meta Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071188241","display_name":"Saurabh Mishra","orcid":"https://orcid.org/0000-0001-8898-6609"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Saurabh Mishra","raw_affiliation_strings":["Meta Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061570110","display_name":"Siqi Yan","orcid":"https://orcid.org/0000-0002-5905-3006"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Siqi Yan","raw_affiliation_strings":["Meta Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062652103","display_name":"Yicong Du","orcid":"https://orcid.org/0000-0002-3523-7476"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yicong Du","raw_affiliation_strings":["Meta Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119635135","display_name":"Elzbieta Krepska","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Elzbieta Krepska","raw_affiliation_strings":["Meta Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032599348","display_name":"Intaik Park","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Intaik Park","raw_affiliation_strings":["Meta Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084150047","display_name":"Min Ni","orcid":"https://orcid.org/0000-0001-6382-0848"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Min Ni","raw_affiliation_strings":["Meta Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006968556","display_name":"Qunshu Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qunshu Zhang","raw_affiliation_strings":["Meta Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Inc","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5104910007","display_name":"Shen Li","orcid":"https://orcid.org/0000-0003-2947-3787"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shen Li","raw_affiliation_strings":["Meta Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Inc","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":16,"corresponding_author_ids":["https://openalex.org/A5001847888"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34429618,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"18","issue":"12","first_page":"4978","last_page":"4990"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9994000196456909,"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":0.9994000196456909,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9815000295639038,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.98089998960495,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/goodput","display_name":"Goodput","score":0.7581999897956848},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.7283999919891357},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5992000102996826},{"id":"https://openalex.org/keywords/delta","display_name":"Delta","score":0.553600013256073},{"id":"https://openalex.org/keywords/production","display_name":"Production (economics)","score":0.43220001459121704},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.3797999918460846}],"concepts":[{"id":"https://openalex.org/C94022561","wikidata":"https://www.wikidata.org/wiki/Q1172393","display_name":"Goodput","level":4,"score":0.7581999897956848},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.7283999919891357},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7060999870300293},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5992000102996826},{"id":"https://openalex.org/C5072461","wikidata":"https://www.wikidata.org/wiki/Q49506","display_name":"Delta","level":2,"score":0.553600013256073},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.43220001459121704},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.3797999918460846},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.3167000114917755},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3111000061035156},{"id":"https://openalex.org/C2992770021","wikidata":"https://www.wikidata.org/wiki/Q7247850","display_name":"Production model","level":3,"score":0.29319998621940613},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.28690001368522644},{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.2865999937057495},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.2809999883174896},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.27970001101493835},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.2705000042915344},{"id":"https://openalex.org/C82753439","wikidata":"https://www.wikidata.org/wiki/Q1419090","display_name":"Industrial production","level":2,"score":0.2615000009536743},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.26080000400543213}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3750601.3750621","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3750601.3750621","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W95608104","https://openalex.org/W2512971201","https://openalex.org/W2947737663","https://openalex.org/W2984020950","https://openalex.org/W3010969086","https://openalex.org/W3197720002","https://openalex.org/W4226012237","https://openalex.org/W4226343359","https://openalex.org/W4296591817","https://openalex.org/W4385270365","https://openalex.org/W4386768656","https://openalex.org/W4387302750"],"related_works":[],"abstract_inverted_index":{"In":[0],"large-scale":[1],"industrial":[2,76],"recommendation":[3],"systems,":[4],"model":[5,32,45,71],"checkpoints":[6,33,92,101],"are":[7,53],"instrumental":[8],"in":[9,36,102,117],"maintaining":[10,121],"training":[11,96,125],"goodput":[12],"and":[13,19,51,59,89,98,105],"numerical":[14],"correctness":[15],"during":[16],"system":[17],"failures":[18],"job":[20],"preemptions.":[21],"The":[22],"increasing":[23],"prevalence":[24],"of":[25],"multi-terabyte":[26],"models":[27],"has":[28],"rendered":[29],"frequent":[30],"regular":[31],"impractical,":[34],"resulting":[35],"substantial":[37],"lost":[38],"progress":[39],"when":[40],"recovering":[41],"from":[42],"failures.":[43],"As":[44],"sizes":[46],"continue":[47],"to":[48,55,69],"grow,":[49],"researchers":[50],"practitioners":[52],"compelled":[54],"investigate":[56],"more":[57],"efficient":[58],"scalable":[60],"solutions.":[61],"This":[62],"paper":[63],"presents":[64],"DECK,":[65],"a":[66,114],"novel":[67],"approach":[68],"delta":[70,83,91,100],"checkpointing":[72],"designed":[73],"for":[74],"real-world":[75],"systems.":[77],"Specifically,":[78],"DECK":[79,112],"focuses":[80],"on":[81,124],"extracting":[82],"states":[84],"with":[85],"near-zero":[86],"overhead,":[87],"staging":[88],"streaming":[90],"without":[93],"interrupting":[94],"the":[95],"process,":[97],"merging":[99],"an":[103],"optimal":[104],"decoupled":[106],"manner.":[107],"Experimental":[108],"results":[109],"demonstrate":[110],"that":[111],"achieves":[113],"12-fold":[115],"increase":[116],"checkpoint":[118],"frequency":[119],"while":[120],"negligible":[122],"impact":[123],"throughput,":[126],"thereby":[127],"attaining":[128],"state-of-the-art":[129],"(SOTA)":[130],"production":[131],"performance.":[132]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}