{"id":"https://openalex.org/W2948438818","doi":null,"title":"The case for unifying data loading in machine learning clusters","display_name":"The case for unifying data loading in machine learning clusters","publication_year":2019,"publication_date":"2019-07-08","ids":{"openalex":"https://openalex.org/W2948438818","mag":"2948438818"},"language":"en","primary_location":{"id":"mag:2948438818","doi":null,"is_oa":false,"landing_page_url":"https://www.usenix.org/system/files/hotcloud19-paper-kakaraparthy.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306418654","display_name":"IEEE International Conference on Cloud Computing Technology and Science","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"IEEE International Conference on Cloud Computing Technology and Science","raw_type":null},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":[],"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/A5029848318","display_name":"Aarati Kakaraparthy","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aarati Kakaraparthy","raw_affiliation_strings":["University of Wisconsin, Madison & Microsoft Gray Systems Lab, Madison"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wisconsin, Madison & Microsoft Gray Systems Lab, Madison","institution_ids":["https://openalex.org/I1290206253","https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018260641","display_name":"Abhay Venkatesh","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abhay Venkatesh","raw_affiliation_strings":["University of Wisconsin-Madison, #TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison, #TAB#","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011102459","display_name":"Amar Phanishayee","orcid":"https://orcid.org/0009-0001-2777-1118","observed_orcids":["https://orcid.org/0009-0001-2777-1118"]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amar Phanishayee","raw_affiliation_strings":["[Microsoft Res., Redmond]"],"raw_orcid":"https://orcid.org/0009-0001-2777-1118","affiliations":[{"raw_affiliation_string":"[Microsoft Res., Redmond]","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082710354","display_name":"Shivaram Venkataraman","orcid":"https://orcid.org/0000-0001-9575-7935","observed_orcids":["https://orcid.org/0000-0001-9575-7935"]},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shivaram Venkataraman","raw_affiliation_strings":["University of Wisconsin-Madison, #TAB#"],"raw_orcid":"https://orcid.org/0000-0001-9575-7935","affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison, #TAB#","institution_ids":["https://openalex.org/I135310074"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1778,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.78558723,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"12","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9872999787330627,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9872999787330627,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.004000000189989805,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.0027000000700354576,"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/i-o-cost-reduction","display_name":"I/O cost reduction","score":0.8519999980926514},{"id":"https://openalex.org/keywords/hyperparameter-optimization","display_name":"hyperparameter optimization","score":0.875},{"id":"https://openalex.org/keywords/distributed-data-access","display_name":"distributed data access","score":0.8100000023841858},{"id":"https://openalex.org/keywords/data-preprocessing","display_name":"data preprocessing","score":0.6819999814033508},{"id":"https://openalex.org/keywords/storage-media","display_name":"storage media","score":0.49000000953674316}],"concepts":[{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.8230135440826416},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.81383216381073},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.7366102933883667},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.573248028755188},{"id":"https://openalex.org/C7545210","wikidata":"https://www.wikidata.org/wiki/Q838123","display_name":"Data redundancy","level":2,"score":0.5567695498466492},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5471519231796265},{"id":"https://openalex.org/C2775941552","wikidata":"https://www.wikidata.org/wiki/Q25212305","display_name":"Isolation (microbiology)","level":2,"score":0.5019190311431885},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.48533573746681213},{"id":"https://openalex.org/C2779965156","wikidata":"https://www.wikidata.org/wiki/Q5227350","display_name":"Data sharing","level":3,"score":0.47475746273994446},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4326307475566864},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.415639191865921},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3322097063064575},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3221909999847412},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.21916744112968445},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1430169641971588},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C89423630","wikidata":"https://www.wikidata.org/wiki/Q7193","display_name":"Microbiology","level":1,"score":0.0},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C204787440","wikidata":"https://www.wikidata.org/wiki/Q188504","display_name":"Alternative medicine","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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":"mag:2948438818","doi":null,"is_oa":false,"landing_page_url":"https://www.usenix.org/system/files/hotcloud19-paper-kakaraparthy.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306418654","display_name":"IEEE International Conference on Cloud Computing Technology and Science","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"IEEE International Conference on Cloud Computing Technology and Science","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.4943999946117401,"id":"https://metadata.un.org/sdg/9"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1480850417","https://openalex.org/W2119885577","https://openalex.org/W2163605009","https://openalex.org/W2165068957","https://openalex.org/W2168395296","https://openalex.org/W2406836379","https://openalex.org/W2525217999","https://openalex.org/W2576802160","https://openalex.org/W2742513757","https://openalex.org/W2775795276","https://openalex.org/W2789753290","https://openalex.org/W2899771611","https://openalex.org/W2963815651","https://openalex.org/W2963933775","https://openalex.org/W3118608800"],"related_works":["https://openalex.org/W4414427843","https://openalex.org/W3095429755","https://openalex.org/W6940881053","https://openalex.org/W4388041378","https://openalex.org/W3204802562","https://openalex.org/W2337745255","https://openalex.org/W2069657673","https://openalex.org/W4307478983","https://openalex.org/W2381524109","https://openalex.org/W3102385572"],"abstract_inverted_index":{"Training":[0],"machine":[1,94],"learning":[2,95],"models":[3],"involves":[4],"iteratively":[5],"fetching":[6],"and":[7,22,53,78,138,164,191],"pre-processing":[8,80],"batches":[9],"of":[10,28,124],"data.":[11],"Conventionally,":[12],"popular":[13],"ML":[14],"frameworks":[15,175],"implement":[16],"data":[17,52,91,101,125,135,153,168,185],"loading":[18,92,102,126,169],"within":[19],"a":[20,29,61,106,110,133,140,145,166],"job":[21],"focus":[23],"on":[24,82,176],"improving":[25],"the":[26,50,87,99,115,122],"performance":[27],"single":[30,107],"job.":[31,129],"However,":[32],"such":[33],"an":[34],"approach":[35],"is":[36],"inefficient":[37],"in":[38,93,127,148,162],"shared":[39,177],"clusters":[40,96],"where":[41],"multiple":[42],"training":[43],"jobs":[44],"are":[45],"likely":[46],"to":[47,75,121,182],"be":[48],"accessing":[49],"same":[51],"duplicating":[54],"operations.":[55],"To":[56],"illustrate":[57],"this,":[58],"we":[59,71,85,157],"present":[60,139],"case":[62,88],"study":[63],"which":[64],"reveals":[65],"that":[66,118,143,171],"for":[67,89],"hyper-parameter":[68],"tuning":[69],"experiments,":[70],"can":[72,113,172],"reduce":[73],"up":[74],"89%":[76],"I/O":[77,149],"97%":[79],"redundancy.\r\n\r\nBased":[81],"this":[83],"observation,":[84],"make":[86],"unifying":[90],"by":[97],"bringing":[98],"isolated":[100],"systems":[103],"together":[104],"into":[105],"system.":[108],"Such":[109],"system":[111],"architecture":[112],"remove":[114],"aforementioned":[116],"redundancies":[117],"arise":[119],"due":[120],"isolation":[123],"each":[128],"We":[130],"introduce":[131],"OneAccess,":[132],"unified":[134,167],"access":[136],"layer":[137,170],"prototype":[141],"implementation":[142],"shows":[144],"47.3%":[146],"improvement":[147],"cost":[150],"when":[151],"sharing":[152],"across":[154,174],"jobs.":[155],"Finally":[156],"discuss":[158],"open":[159],"research":[160],"challenges":[161],"designing":[163],"developing":[165],"run":[173],"multi-tenant":[178],"clusters,":[179],"including":[180],"how":[181],"handle":[183],"distributed":[184],"access,":[186],"support":[187],"diverse":[188],"sampling":[189],"schemes,":[190],"exploit":[192],"new":[193],"storage":[194],"media.":[195]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2019-06-14T00:00:00"}