{"id":"https://openalex.org/W4406458749","doi":"https://doi.org/10.1109/bigdata62323.2024.10825421","title":"An Overview of the Data-Loader Landscape: Comparative Performance Analysis","display_name":"An Overview of the Data-Loader Landscape: Comparative Performance Analysis","publication_year":2024,"publication_date":"2024-12-15","ids":{"openalex":"https://openalex.org/W4406458749","doi":"https://doi.org/10.1109/bigdata62323.2024.10825421"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata62323.2024.10825421","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825421","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","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/A5053398628","display_name":"Iason Ofeidis","orcid":"https://orcid.org/0000-0001-8206-8321"},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Iason Ofeidis","raw_affiliation_strings":["Yale University,New Haven,CT,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yale University,New Haven,CT,USA","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065231637","display_name":"Diego Kiedanski","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Diego Kiedanski","raw_affiliation_strings":["Tryolabs,Montevideo,Uruguay"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tryolabs,Montevideo,Uruguay","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014892027","display_name":"Leandros Tassiulas","orcid":"https://orcid.org/0000-0003-0932-774X"},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Leandros Tassiulas","raw_affiliation_strings":["Yale University,New Haven,CT,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yale University,New Haven,CT,USA","institution_ids":["https://openalex.org/I32971472"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.28317281,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"360","last_page":"367"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9991000294685364,"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":0.9991000294685364,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9961000084877014,"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"}},{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9952999949455261,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/loader","display_name":"Loader","score":0.8534094095230103},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6926811337471008},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.33377566933631897},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.084564208984375}],"concepts":[{"id":"https://openalex.org/C2779041774","wikidata":"https://www.wikidata.org/wiki/Q650550","display_name":"Loader","level":2,"score":0.8534094095230103},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6926811337471008},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.33377566933631897},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.084564208984375}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata62323.2024.10825421","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825421","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W2194775991","https://openalex.org/W2525778437","https://openalex.org/W2618530766","https://openalex.org/W2889985731","https://openalex.org/W2898496135","https://openalex.org/W2942231644","https://openalex.org/W2963674387","https://openalex.org/W2966048283","https://openalex.org/W2971624117","https://openalex.org/W2972087877","https://openalex.org/W2977730164","https://openalex.org/W2997749524","https://openalex.org/W2998689333","https://openalex.org/W3001279689","https://openalex.org/W3002842489","https://openalex.org/W3006388426","https://openalex.org/W3006889321","https://openalex.org/W3036878841","https://openalex.org/W3086105743","https://openalex.org/W3099319035","https://openalex.org/W3105067168","https://openalex.org/W3106099468","https://openalex.org/W3138303811","https://openalex.org/W3173453991","https://openalex.org/W3185250692","https://openalex.org/W4213251304","https://openalex.org/W4295312788","https://openalex.org/W4296973065","https://openalex.org/W4308758967","https://openalex.org/W4386075570","https://openalex.org/W6620707391","https://openalex.org/W6727690538","https://openalex.org/W6766978945","https://openalex.org/W6772383348","https://openalex.org/W6774025309","https://openalex.org/W6780671031","https://openalex.org/W6803835703","https://openalex.org/W6843591696","https://openalex.org/W6846763256"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2365193102","https://openalex.org/W2343312170","https://openalex.org/W2392969333","https://openalex.org/W2380220463","https://openalex.org/W2745521454","https://openalex.org/W2363418592","https://openalex.org/W2061615910"],"abstract_inverted_index":{"The":[0,104],"efficiency":[1],"of":[2,17,71,81,118],"Deep":[3],"Learning":[4],"(DL)":[5],"training":[6,40],"jobs":[7],"is":[8],"critically":[9],"dependent":[10],"on":[11,121],"dataloaders,":[12],"which":[13,151],"facilitate":[14],"the":[15,57,64,116,142,153],"transfer":[16],"data":[18,29,98,122,149],"from":[19],"storage":[20],"to":[21,155],"DL-accelerated":[22],"hardware":[23],"during":[24],"training.":[25],"Recent":[26],"advancements":[27],"in":[28,38,44,108],"loading":[30,123],"technology":[31],"have":[32],"demonstrated":[33],"significant":[34],"improvements,":[35],"not":[36],"only":[37],"reducing":[39],"times":[41],"but":[42],"also":[43],"introducing":[45],"capabilities":[46],"such":[47],"as":[48,59],"seamless":[49],"integration":[50],"with":[51,130],"cloud":[52],"storage.":[53],"This":[54],"paper":[55],"examines":[56],"dataloader":[58],"a":[60,68,78],"distinct":[61],"component":[62],"within":[63],"DL":[65,148],"workflow,":[66],"offering":[67],"detailed":[69],"analysis":[70],"its":[72],"structure":[73],"and":[74,101,111,137,158],"functionalities.":[75],"We":[76],"present":[77],"systematic":[79],"evaluation":[80,105],"various":[82],"dataloading":[83],"libraries,":[84],"investigating":[85],"their":[86],"performance":[87],"across":[88],"different":[89],"configurations,":[90],"including":[91],"worker":[92],"count,":[93],"batch":[94],"size,":[95],"GPU":[96],"scaling,":[97],"access":[99],"patterns":[100],"remote":[102],"loading.":[103],"highlights":[106],"trade-offs":[107],"functionality,":[109],"usability,":[110],"performance.":[112],"Additionally,":[113],"we":[114,140],"examine":[115],"impact":[117],"dataset":[119],"characteristics":[120],"performance,":[124],"showing":[125],"that":[126],"throughput":[127],"decreases":[128],"exponentially":[129],"image":[131],"resolution.":[132],"To":[133],"support":[134],"ongoing":[135],"research":[136],"practical":[138],"advancements,":[139],"introduce":[141],"first":[143],"open-source":[144],"benchmarking":[145],"suite":[146],"for":[147],"loading,":[150],"allows":[152],"community":[154],"replicate,":[156],"extend,":[157],"build":[159],"upon":[160],"our":[161],"experiments.":[162]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}