{"id":"https://openalex.org/W4417002484","doi":"https://doi.org/10.1109/tbdata.2025.3640011","title":"Lafa: Unlocking Superior Memory Efficiency via Adaptive Metadata Strategy for Scalable Large-Scale Dataset Loading","display_name":"Lafa: Unlocking Superior Memory Efficiency via Adaptive Metadata Strategy for Scalable Large-Scale Dataset Loading","publication_year":2025,"publication_date":"2025-12-04","ids":{"openalex":"https://openalex.org/W4417002484","doi":"https://doi.org/10.1109/tbdata.2025.3640011"},"language":null,"primary_location":{"id":"doi:10.1109/tbdata.2025.3640011","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tbdata.2025.3640011","pdf_url":null,"source":{"id":"https://openalex.org/S2491400915","display_name":"IEEE Transactions on Big Data","issn_l":"2332-7790","issn":["2332-7790","2372-2096"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Big Data","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":null,"display_name":"Cong Wang","orcid":"https://orcid.org/0000-0002-4539-2525"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Cong Wang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China","University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0002-4539-2525","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yang Luo","orcid":"https://orcid.org/0009-0009-2858-3774"},"institutions":[{"id":"https://openalex.org/I4210158493","display_name":"Open Source Science Project","ror":"https://ror.org/0523sbv14","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210158493"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yang Luo","raw_affiliation_strings":["MindSpore open source project, Shenzhen, China","MindSpore open source project, China"],"raw_orcid":"https://orcid.org/0009-0009-2858-3774","affiliations":[{"raw_affiliation_string":"MindSpore open source project, Shenzhen, China","institution_ids":["https://openalex.org/I4210158493"]},{"raw_affiliation_string":"MindSpore open source project, China","institution_ids":["https://openalex.org/I4210158493"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ke Wang","orcid":"https://orcid.org/0009-0001-9763-0134"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ke Wang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China","University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0009-0001-9763-0134","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hui Zhang","orcid":"https://orcid.org/0000-0002-6539-7470"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Zhang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China","University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0002-6539-7470","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084538628","display_name":"Naijie Gu","orcid":"https://orcid.org/0000-0002-8898-0896"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Naijie Gu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China","University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090458052","display_name":"Ran Zhang","orcid":"https://orcid.org/0000-0002-7630-1251"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ran Zhang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China","University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000783014","display_name":"Wenzhuo Du","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenzhuo Du","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China","University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0009-0003-8527-7307","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100616400","display_name":"Fan Yu","orcid":"https://orcid.org/0000-0002-0576-7396"},"institutions":[{"id":"https://openalex.org/I4210158493","display_name":"Open Source Science Project","ror":"https://ror.org/0523sbv14","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210158493"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fan Yu","raw_affiliation_strings":["MindSpore open source project, Shenzhen, China","MindSpore open source project, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MindSpore open source project, Shenzhen, China","institution_ids":["https://openalex.org/I4210158493"]},{"raw_affiliation_string":"MindSpore open source project, China","institution_ids":["https://openalex.org/I4210158493"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048818071","display_name":"Jun Yu","orcid":"https://orcid.org/0000-0002-3197-8103"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Yu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China","University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0002-3197-8103","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.49651186,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"12","issue":"2","first_page":"674","last_page":"687"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.28459998965263367,"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":0.28459998965263367,"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/T14347","display_name":"Big Data and Digital Economy","score":0.15719999372959137,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.12129999697208405,"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/metadata","display_name":"Metadata","score":0.7739999890327454},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7425000071525574},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6586999893188477},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.4392000138759613},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.36329999566078186},{"id":"https://openalex.org/keywords/data-access","display_name":"Data access","score":0.3089999854564667}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9128000140190125},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.7739999890327454},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7425000071525574},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6586999893188477},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.48649999499320984},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.4392000138759613},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.36329999566078186},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3154999911785126},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.3089999854564667},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.2921999990940094},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.2777999937534332},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.2635999917984009},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2549000084400177}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tbdata.2025.3640011","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tbdata.2025.3640011","pdf_url":null,"source":{"id":"https://openalex.org/S2491400915","display_name":"IEEE Transactions on Big Data","issn_l":"2332-7790","issn":["2332-7790","2372-2096"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Big Data","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G450612882","display_name":null,"funder_award_id":"62276242","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"rapid":[1],"growth":[2],"of":[3,136],"deep":[4],"learning":[5],"models":[6],"and":[7,22,41,68,80,93,106,153],"the":[8,65,146],"increasing":[9],"demand":[10],"for":[11,19,58,122],"large-scale":[12,60],"datasets":[13,37],"have":[14],"posed":[15],"unprece":[16],"dented":[17],"challenges":[18],"data":[20,98],"loading":[21,55,71,81],"memory":[23,43,78,91,115,131],"management.":[24],"Existing":[25],"frameworks":[26],"(e.g.,":[27],"PyTorch,":[28,151],"TensorFlow)":[29],"often":[30],"encounter":[31],"performance":[32],"bottlenecks":[33],"when":[34],"handling":[35],"large":[36],"resulting":[38],"in":[39],"inefficiencies":[40],"excessive":[42],"usage.":[44],"To":[45],"address":[46],"these":[47],"issues,":[48],"we":[49],"propose":[50],"Lafa,":[51],"a":[52,85,134],"dynamic":[53],"metadata":[54],"mechanism":[56],"optimized":[57],"efficient":[59],"dataset":[61,142],"processing.":[62],"Lafa":[63,112,128],"introduces":[64],".Lafa":[66],"format":[67],"an":[69],"adaptive":[70],"strategy":[72],"with":[73,84],"three":[74],"modes":[75],"to":[76,118,138,145],"balance":[77],"usage":[79],"performance,":[82],"along":[83],"local":[86],"shuffle":[87],"approach":[88],"that":[89,111],"reduces":[90,129],"overhead":[92],"computational":[94],"complexity":[95],"while":[96],"preserving":[97],"randomness.":[99],"Experimental":[100],"results":[101],"on":[102],"GPU":[103],"(RTX":[104],"3090)":[105],"Ascend":[107],"(910A)":[108],"platforms":[109],"demonstrate":[110],"significantly":[113],"improves":[114],"efficiency":[116],"compared":[117],"existing":[119],"frameworks.":[120],"Specifically,":[121],"every":[123],"10":[124],"million":[125],"samples":[126],"loaded,":[127],"additional":[130],"consumption":[132],"by":[133],"factor":[135],"1.33\u00d7":[137],"31.34\u00d7":[139],"across":[140],"various":[141],"types,":[143],"relative":[144],"most":[147],"memory-efficient":[148],"baseline":[149],"among":[150],"TensorFlow,":[152],"MindSpore.":[154]},"counts_by_year":[],"updated_date":"2026-03-14T06:41:57.775601","created_date":"2025-12-04T00:00:00"}