{"id":"https://openalex.org/W4283070722","doi":"https://doi.org/10.1145/3526058.3535453","title":"Large Scale Caching and Streaming of Training Data for Online Deep Learning","display_name":"Large Scale Caching and Streaming of Training Data for Online Deep Learning","publication_year":2022,"publication_date":"2022-06-23","ids":{"openalex":"https://openalex.org/W4283070722","doi":"https://doi.org/10.1145/3526058.3535453"},"language":"en","primary_location":{"id":"doi:10.1145/3526058.3535453","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3526058.3535453","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3526058.3535453","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th Workshop on AI and Scientific Computing at Scale using Flexible Computing Infrastructures","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3526058.3535453","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100454005","display_name":"Jie Liu","orcid":"https://orcid.org/0000-0001-6209-6886"},"institutions":[{"id":"https://openalex.org/I156087764","display_name":"University of California, Merced","ror":"https://ror.org/00d9ah105","country_code":"US","type":"education","lineage":["https://openalex.org/I156087764"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jie Liu","raw_affiliation_strings":["University of California, Merced, Merced, CA, USA","UC Merced - University of California [Merced] (5200 N. Lake Road, \r\nMerced, CA 95343 - United States)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Merced, Merced, CA, USA","institution_ids":["https://openalex.org/I156087764"]},{"raw_affiliation_string":"UC Merced - University of California [Merced] (5200 N. Lake Road, \r\nMerced, CA 95343 - United States)","institution_ids":["https://openalex.org/I156087764"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085745891","display_name":"Bogdan Nicolae","orcid":"https://orcid.org/0000-0002-0661-7509"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bogdan Nicolae","raw_affiliation_strings":["Argonne National Laboratory, Lemont, IL, USA","ANL - Argonne National Laboratory [Lemont] (9700 S Cass Ave B109, Lemont, IL, 60439 - United States)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, Lemont, IL, USA","institution_ids":["https://openalex.org/I1282105669"]},{"raw_affiliation_string":"ANL - Argonne National Laboratory [Lemont] (9700 S Cass Ave B109, Lemont, IL, 60439 - United States)","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100407387","display_name":"Dong Li","orcid":"https://orcid.org/0000-0001-9336-0694"},"institutions":[{"id":"https://openalex.org/I156087764","display_name":"University of California, Merced","ror":"https://ror.org/00d9ah105","country_code":"US","type":"education","lineage":["https://openalex.org/I156087764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dong Li","raw_affiliation_strings":["University of California, Merced, Merced, CA, USA","UC Merced - University of California [Merced] (5200 N. Lake Road, \r\nMerced, CA 95343 - United States)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Merced, Merced, CA, USA","institution_ids":["https://openalex.org/I156087764"]},{"raw_affiliation_string":"UC Merced - University of California [Merced] (5200 N. Lake Road, \r\nMerced, CA 95343 - United States)","institution_ids":["https://openalex.org/I156087764"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020776475","display_name":"Justin M. Wozniak","orcid":"https://orcid.org/0000-0002-2441-2048"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Justin M. Wozniak","raw_affiliation_strings":["Argonne National Laboratory, Lemont, IL, USA","ANL - Argonne National Laboratory [Lemont] (9700 S Cass Ave B109, Lemont, IL, 60439 - United States)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, Lemont, IL, USA","institution_ids":["https://openalex.org/I1282105669"]},{"raw_affiliation_string":"ANL - Argonne National Laboratory [Lemont] (9700 S Cass Ave B109, Lemont, IL, 60439 - United States)","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038566298","display_name":"Tekin Bi\u00e7er","orcid":"https://orcid.org/0000-0002-8428-5159"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tekin Bicer","raw_affiliation_strings":["Argonne National Laboratory, Lemont, IL, USA","ANL - Argonne National Laboratory [Lemont] (9700 S Cass Ave B109, Lemont, IL, 60439 - United States)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, Lemont, IL, USA","institution_ids":["https://openalex.org/I1282105669"]},{"raw_affiliation_string":"ANL - Argonne National Laboratory [Lemont] (9700 S Cass Ave B109, Lemont, IL, 60439 - United States)","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101649257","display_name":"Zhengchun Liu","orcid":"https://orcid.org/0000-0002-6647-4423"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhengchun Liu","raw_affiliation_strings":["Argonne National Laboratory, Lemont, IL, USA","ANL - Argonne National Laboratory [Lemont] (9700 S Cass Ave B109, Lemont, IL, 60439 - United States)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, Lemont, IL, USA","institution_ids":["https://openalex.org/I1282105669"]},{"raw_affiliation_string":"ANL - Argonne National Laboratory [Lemont] (9700 S Cass Ave B109, Lemont, IL, 60439 - United States)","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032231503","display_name":"Ian Foster","orcid":"https://orcid.org/0000-0003-2129-5269"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ian Foster","raw_affiliation_strings":["Argonne National Laboratory, Lemont, IL, USA","ANL - Argonne National Laboratory [Lemont] (9700 S Cass Ave B109, Lemont, IL, 60439 - United States)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, Lemont, IL, USA","institution_ids":["https://openalex.org/I1282105669"]},{"raw_affiliation_string":"ANL - Argonne National Laboratory [Lemont] (9700 S Cass Ave B109, Lemont, IL, 60439 - United States)","institution_ids":["https://openalex.org/I1282105669"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100454005"],"corresponding_institution_ids":["https://openalex.org/I156087764"],"apc_list":null,"apc_paid":null,"fwci":1.2486,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.8276909,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"19","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9972000122070312,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8782981634140015},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7356136441230774},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5040942430496216},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.47070834040641785},{"id":"https://openalex.org/keywords/file-system","display_name":"File system","score":0.46196314692497253},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.44091376662254333},{"id":"https://openalex.org/keywords/pipeline-transport","display_name":"Pipeline transport","score":0.4402758479118347},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.43457192182540894},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4332903027534485},{"id":"https://openalex.org/keywords/concurrency","display_name":"Concurrency","score":0.42549893260002136},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4249574542045593},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.4234883189201355},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4093582034111023},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4074878990650177},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.25120991468429565},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.20548078417778015},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.15971538424491882}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8782981634140015},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7356136441230774},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5040942430496216},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.47070834040641785},{"id":"https://openalex.org/C2780940931","wikidata":"https://www.wikidata.org/wiki/Q174989","display_name":"File system","level":2,"score":0.46196314692497253},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.44091376662254333},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.4402758479118347},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.43457192182540894},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4332903027534485},{"id":"https://openalex.org/C193702766","wikidata":"https://www.wikidata.org/wiki/Q1414548","display_name":"Concurrency","level":2,"score":0.42549893260002136},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4249574542045593},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.4234883189201355},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4093582034111023},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4074878990650177},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25120991468429565},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.20548078417778015},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.15971538424491882},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C87717796","wikidata":"https://www.wikidata.org/wiki/Q146326","display_name":"Environmental engineering","level":1,"score":0.0},{"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},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3526058.3535453","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3526058.3535453","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3526058.3535453","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th Workshop on AI and Scientific Computing at Scale using Flexible Computing Infrastructures","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-03694669v1","is_oa":true,"landing_page_url":"https://hal.science/hal-03694669","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"12th Workshop on AI and Scientific Computing at Scale using Flexible Computing Infrastructures, Jul 2022, Minneapolis, United States. ⟨10.1145/3526058.3535453⟩","raw_type":"Conference papers"},{"id":"pmh:oai:osti.gov:1887185","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1887185","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"doi:10.1145/3526058.3535453","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3526058.3535453","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3526058.3535453","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th Workshop on AI and Scientific Computing at Scale using Flexible Computing Infrastructures","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4283070722.pdf","grobid_xml":"https://content.openalex.org/works/W4283070722.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W1859126261","https://openalex.org/W2150595230","https://openalex.org/W2194775991","https://openalex.org/W2566699981","https://openalex.org/W2788388592","https://openalex.org/W2961595369","https://openalex.org/W2962747323","https://openalex.org/W2963304552","https://openalex.org/W2964189064","https://openalex.org/W2969388332","https://openalex.org/W2977730164","https://openalex.org/W2998689333","https://openalex.org/W3039165326","https://openalex.org/W3043360281","https://openalex.org/W3046253174","https://openalex.org/W3088514010","https://openalex.org/W3091688522","https://openalex.org/W3105067168","https://openalex.org/W3196732841","https://openalex.org/W3206418153","https://openalex.org/W6829155664"],"related_works":["https://openalex.org/W4380433113","https://openalex.org/W4386072068","https://openalex.org/W252339960","https://openalex.org/W2390529043","https://openalex.org/W2378320433","https://openalex.org/W2358343511","https://openalex.org/W2051877971","https://openalex.org/W1970117064","https://openalex.org/W1787170397","https://openalex.org/W4292347844"],"abstract_inverted_index":{"The":[0],"training":[1,36,117,122,158,175],"of":[2,190,196],"deep":[3],"neural":[4],"network":[5],"models":[6,70],"on":[7,132,163,193],"large":[8],"data":[9,47,59,99,133,142,198],"remains":[10],"a":[11,23,178],"difficult":[12],"problem,":[13],"despite":[14],"progress":[15],"towards":[16,78],"scalable":[17],"techniques.":[18,159],"In":[19,55,94],"particular,":[20],"there":[21],"is":[22,63],"mismatch":[24],"between":[25],"the":[26,39,146,168,174,188,191,194,197],"random":[27],"but":[28],"predetermined":[29],"order":[30,111],"in":[31,110,119,172],"which":[32,44],"AI":[33],"flows":[34],"select":[35],"samples":[37,118,176],"and":[38,105,123,141,144,148],"streaming":[40,106,129],"I/O":[41,169],"patterns":[42],"for":[43],"traditional":[45],"HPC":[46],"storage":[48],"(e.g.,":[49],"parallel":[50,179],"file":[51,180],"systems)":[52],"are":[53,60],"designed.":[54],"addition,":[56],"as":[57],"more":[58],"obtained,":[61],"it":[62],"feasible":[64],"neither":[65],"simply":[66],"to":[67,73,82,88,112,116],"train":[68,83],"learning":[69],"incrementally,":[71],"due":[72,87],"catastrophic":[74],"forgetting":[75],"(i.e.,":[76],"bias":[77],"new":[79],"samples),":[80],"nor":[81],"frequently":[84],"from":[85,177],"scratch,":[86],"prohibitive":[89],"time":[90],"and/or":[91],"resource":[92],"constraints.":[93],"this":[95],"paper,":[96],"we":[97],"study":[98],"management":[100],"techniques":[101],"that":[102,135,150,166],"combine":[103],"caching":[104],"with":[107,156],"rehearsal":[108],"support":[109],"enable":[113],"efficient":[114],"access":[115],"both":[120],"offline":[121],"continual":[124],"learning.":[125],"We":[126,160],"revisit":[127],"state-of-art":[128],"approaches":[130],"based":[131],"pipelines":[134],"transparently":[136],"handle":[137],"prefetching,":[138],"caching,":[139],"shuffling,":[140],"augmentation,":[143],"discuss":[145],"challenges":[147],"opportunities":[149],"arise":[151],"when":[152],"combining":[153],"these":[154],"methods":[155],"data-parallel":[157],"also":[161],"report":[162],"preliminary":[164],"experiments":[165],"evaluate":[167],"overheads":[170],"involved":[171],"accessing":[173],"system":[181],"(PFS)":[182],"under":[183],"several":[184],"concurrency":[185],"scenarios,":[186],"highlighting":[187],"impact":[189],"PFS":[192],"design":[195],"pipelines.":[199]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-05-21T09:19:25.381259","created_date":"2025-10-10T00:00:00"}