{"id":"https://openalex.org/W4388937844","doi":"https://doi.org/10.1109/tc.2023.3336161","title":"MMDataLoader: Reusing Preprocessed Data Among Concurrent Model Training Tasks","display_name":"MMDataLoader: Reusing Preprocessed Data Among Concurrent Model Training Tasks","publication_year":2023,"publication_date":"2023-11-23","ids":{"openalex":"https://openalex.org/W4388937844","doi":"https://doi.org/10.1109/tc.2023.3336161"},"language":"en","primary_location":{"id":"doi:10.1109/tc.2023.3336161","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2023.3336161","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","0016-9340","1557-9956","2326-3814"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computers","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/A5022262922","display_name":"Hai Jin","orcid":"https://orcid.org/0000-0002-3934-7605"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hai Jin","raw_affiliation_strings":["National Engineering Research Center for Big Data Technology and System, Services Computing Technology and System Lab, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-3934-7605","affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Big Data Technology and System, Services Computing Technology and System Lab, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103182519","display_name":"Zhanyang Zhu","orcid":"https://orcid.org/0009-0001-0324-1358"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhanyang Zhu","raw_affiliation_strings":["National Engineering Research Center for Big Data Technology and System, Services Computing Technology and System Lab, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0009-0001-0324-1358","affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Big Data Technology and System, Services Computing Technology and System Lab, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064596191","display_name":"Ligang He","orcid":"https://orcid.org/0000-0002-5671-0576"},"institutions":[{"id":"https://openalex.org/I39555362","display_name":"University of Warwick","ror":"https://ror.org/01a77tt86","country_code":"GB","type":"education","lineage":["https://openalex.org/I39555362"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ligang He","raw_affiliation_strings":["University of Warwick, Coventry, U.K"],"raw_orcid":"https://orcid.org/0000-0002-5671-0576","affiliations":[{"raw_affiliation_string":"University of Warwick, Coventry, U.K","institution_ids":["https://openalex.org/I39555362"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100348239","display_name":"Yuhao Li","orcid":"https://orcid.org/0009-0006-7913-3106"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhao Li","raw_affiliation_strings":["National Engineering Research Center for Big Data Technology and System, Services Computing Technology and System Lab, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0009-0006-7913-3106","affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Big Data Technology and System, Services Computing Technology and System Lab, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058974274","display_name":"Yusheng Hua","orcid":"https://orcid.org/0009-0001-7017-4941"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yusheng Hua","raw_affiliation_strings":["National Engineering Research Center for Big Data Technology and System, Services Computing Technology and System Lab, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0009-0001-7017-4941","affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Big Data Technology and System, Services Computing Technology and System Lab, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016486553","display_name":"Xuanhua Shi","orcid":"https://orcid.org/0000-0001-8451-8656"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuanhua Shi","raw_affiliation_strings":["National Engineering Research Center for Big Data Technology and System, Services Computing Technology and System Lab, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0001-8451-8656","affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Big Data Technology and System, Services Computing Technology and System Lab, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2345,"currency":"USD","value_usd":2345},"apc_paid":null,"fwci":0.7604,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.69564132,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"73","issue":"2","first_page":"510","last_page":"522"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9990000128746033,"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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9990000128746033,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9922000169754028,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9879999756813049,"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/computer-science","display_name":"Computer science","score":0.8619529604911804},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.7023450136184692},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6437195539474487},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5625104904174805},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.5515260696411133},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5332531332969666},{"id":"https://openalex.org/keywords/data-pre-processing","display_name":"Data pre-processing","score":0.5032896399497986},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.4721676707267761},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.42563414573669434},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.42390093207359314},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4117797017097473},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.35843485593795776},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3574315011501312},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.21044397354125977},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.18610501289367676},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.1518985629081726}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8619529604911804},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.7023450136184692},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6437195539474487},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5625104904174805},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.5515260696411133},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5332531332969666},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.5032896399497986},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.4721676707267761},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.42563414573669434},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.42390093207359314},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4117797017097473},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.35843485593795776},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3574315011501312},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.21044397354125977},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.18610501289367676},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.1518985629081726},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tc.2023.3336161","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2023.3336161","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","0016-9340","1557-9956","2326-3814"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computers","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G676909771","display_name":null,"funder_award_id":"2020AAA0108501","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W2064173066","https://openalex.org/W2097998348","https://openalex.org/W2108598243","https://openalex.org/W2113097878","https://openalex.org/W2143612262","https://openalex.org/W2160532515","https://openalex.org/W2169818249","https://openalex.org/W2194775991","https://openalex.org/W2224360389","https://openalex.org/W2279098554","https://openalex.org/W2618530766","https://openalex.org/W2732547613","https://openalex.org/W2765407302","https://openalex.org/W2783482415","https://openalex.org/W2922648309","https://openalex.org/W2954996726","https://openalex.org/W2957236078","https://openalex.org/W2962718439","https://openalex.org/W2962793481","https://openalex.org/W2963125010","https://openalex.org/W2963767194","https://openalex.org/W2964220187","https://openalex.org/W2998508940","https://openalex.org/W3012514909","https://openalex.org/W3034600949","https://openalex.org/W3037946710","https://openalex.org/W3138303811","https://openalex.org/W3173358825","https://openalex.org/W4200282803","https://openalex.org/W4205390421","https://openalex.org/W4206001106","https://openalex.org/W4211182523","https://openalex.org/W4287813281","https://openalex.org/W4295122555","https://openalex.org/W4394662461","https://openalex.org/W6674385629","https://openalex.org/W6677064947","https://openalex.org/W6695314431","https://openalex.org/W6745136726","https://openalex.org/W6747939174","https://openalex.org/W6765518731","https://openalex.org/W6774103200","https://openalex.org/W6776981032","https://openalex.org/W6798611780","https://openalex.org/W6863618527"],"related_works":["https://openalex.org/W2989490741","https://openalex.org/W3092506759","https://openalex.org/W2367545121","https://openalex.org/W4248881655","https://openalex.org/W2482165163","https://openalex.org/W3010890513","https://openalex.org/W120741642","https://openalex.org/W138569904","https://openalex.org/W2390914021","https://openalex.org/W2389417819"],"abstract_inverted_index":{"Data":[0,15],"preprocessing":[1,16,41,84,91,151,176,194],"plays":[2],"an":[3],"important":[4],"role":[5],"in":[6,50],"deep":[7],"learning,":[8],"which":[9,69],"directly":[10],"affects":[11],"the":[12,20,29,35,43,51,103,112,127,175,186,191],"training":[13,57,77,122,164],"efficiency.":[14],"is":[17],"performed":[18],"on":[19,34,42,87,102,185],"CPU.":[21,104],"The":[22,143],"preprocessed":[23,72],"data":[24,40,73,83,96,107,117,132],"are":[25,32,166,197],"then":[26],"fed":[27],"to":[28,61,120,159,182],"models":[30],"that":[31,39,109,146,196],"trained":[33],"GPU.":[36],"We":[37,138],"observe":[38],"CPU":[44],"can":[45,148,178],"potentially":[46],"create":[47],"a":[48,55,82],"bottleneck":[49],"entire":[52],"process":[53],"of":[54,193],"model":[56,76,155,163],"task.":[58],"In":[59],"order":[60],"tackle":[62],"this":[63],"issue,":[64],"we":[65],"have":[66,139],"developed":[67],"MMDataLoader,":[68],"enables":[70],"reusing":[71],"among":[74,199],"multiple":[75],"tasks.":[78,137],"MMDataLoader":[79,124,147],"automatically":[80],"constructs":[81],"pipeline":[85],"based":[86],"each":[88],"task's":[89],"specific":[90,121],"workflow,":[92],"allowing":[93],"for":[94,133],"maximum":[95],"reuse":[97],"and":[98,115,130,190],"reduced":[99],"computing":[100],"workload":[101],"Unlike":[105],"conventional":[106,160],"loaders":[108],"operate":[110],"at":[111,126],"task":[113],"level":[114,129],"provide":[116],"provision":[118],"services":[119],"tasks,":[123],"operates":[125],"server":[128],"provides":[131],"all":[134],"concurrently":[135],"running":[136],"conducted":[140],"extensive":[141],"experiments.":[142],"results":[144],"show":[145],"significantly":[149],"increase":[150,179],"throughput":[152,177],"without":[153],"affecting":[154],"convergence":[156],"when":[157],"compared":[158],"methods":[161],"where":[162],"tasks":[165,173,187],"executed":[167,189],"concurrently.":[168],"For":[169],"instance,":[170],"with":[171],"three":[172],"running,":[174],"by":[180],"1.6x":[181],"3.15x,":[183],"depending":[184],"being":[188],"proportion":[192],"operations":[195],"shared":[198],"them.":[200]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}