{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T21:23:25Z","timestamp":1773696205784,"version":"3.50.1"},"reference-count":49,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2021ZD0110400"],"award-info":[{"award-number":["2021ZD0110400"]}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62276242"],"award-info":[{"award-number":["62276242"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"National Aviation Science Foundation","award":["2022Z071078001"],"award-info":[{"award-number":["2022Z071078001"]}]},{"name":"Hefei Municipal Natural Science Foundation","award":["HZR2431"],"award-info":[{"award-number":["HZR2431"]}]},{"name":"Dreams Foundation of Jianghuai Advance Technology Center","award":["2023-ZM01Z001"],"award-info":[{"award-number":["2023-ZM01Z001"]}]},{"name":"CAAI-MindSpore Open Fund"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Big Data"],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1109\/tbdata.2025.3640011","type":"journal-article","created":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T18:38:34Z","timestamp":1764873514000},"page":"674-687","source":"Crossref","is-referenced-by-count":0,"title":["Lafa: Unlocking Superior Memory Efficiency via Adaptive Metadata Strategy for Scalable Large-Scale Dataset Loading"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4539-2525","authenticated-orcid":false,"given":"Cong","family":"Wang","sequence":"first","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2858-3774","authenticated-orcid":false,"given":"Yang","family":"Luo","sequence":"additional","affiliation":[{"name":"MindSpore open source project, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9763-0134","authenticated-orcid":false,"given":"Ke","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6539-7470","authenticated-orcid":false,"given":"Hui","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Naijie","family":"Gu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ran","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8527-7307","authenticated-orcid":false,"given":"Wenzhuo","family":"Du","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fan","family":"Yu","sequence":"additional","affiliation":[{"name":"MindSpore open source project, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3197-8103","authenticated-orcid":false,"given":"Jun","family":"Yu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01156"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3190508.3190534"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/BIGCOM61073.2023.00036"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3404397.3404472"},{"key":"ref5","article-title":"Pytorch docs: Torch.utils.data","author":"Contributors","year":"2019"},{"issue":"12","key":"ref6","first-page":"2945","article-title":"tf. data: A machine learning data processing framework","volume-title":"Proc. VLDB Endow.","volume":"14","author":"Murray","year":"2021"},{"key":"ref7","article-title":"Fast AI data preprocessing with NVIDIA DALI","author":"Guirao","year":"2019"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2025.3526662"},{"key":"ref9","article-title":"Tfrecord and tf.example","year":"2020"},{"key":"ref10","article-title":"Deep lake: A lakehouse for deep learning","volume-title":"Proc. 13th Annu. Conf. Innovative Data Syst. Res. (CIDR),","author":"Hambardzumyan","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref12","article-title":"Pointer sentinel mixture models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Merity","year":"2017"},{"key":"ref13","first-page":"25278","article-title":"Laion-5b: An open large-scale dataset for training next generation image-text models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Schuhmann","year":"2022"},{"key":"ref14","article-title":"Shapenet: An information-rich 3D model repository","author":"Chang","year":"2015"},{"key":"ref15","article-title":"Ucf101: A dataset of 101 human actions classes from videos in the wild","author":"Soomro","year":"2012"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2014.2325029"},{"key":"ref17","article-title":"Pangu-weather: A 3D high-resolution model for fast and accurate global weather forecast","author":"Bi","year":"2022"},{"key":"ref18","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Brown","year":"2020"},{"key":"ref19","article-title":"Ernie 3.0: Large-scale knowledge enhanced pre-training for language understanding and generation","author":"Sun","year":"2021"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/BigData47090.2019.9005703"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.infsof.2020.106368"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1145\/3194085.3194087","article-title":"Deep learning for self-driving cars: Chances and challenges","volume-title":"Proc. 1st Int. Workshop Softw. Eng. AI Auton. Syst.","author":"Rao","year":"2018"},{"key":"ref23","article-title":"Training deep nets with sublinear memory cost","author":"Chen","year":"2016"},{"key":"ref24","article-title":"Efficient memory management for deep neural net inference","author":"Pisarchyk","year":"2020"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3178487.3178491"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2016.53"},{"key":"ref27","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Paszke","year":"2019"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3611450.3611463"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS53621.2022.00109"},{"key":"ref30","article-title":"Tensorflow: Large-scale machine learning on heterogeneous systems","author":"Abadi","year":"2016"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-19-2879-6_5"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-018-09679-z"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2696365"},{"key":"ref34","first-page":"15","article-title":"Resilient distributed datasets: A Fault-Tolerant abstraction for In-Memory cluster computing","volume-title":"Proc. 9th USENIX Symp. Networked Syst. Des. Implementation","author":"Zaharia","year":"2012"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.14778\/3554821.3554842"},{"key":"ref36","article-title":"Tfrecord and tf.train.example","author":"Developers","year":"2023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/1966895.1966900"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/2934664"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2016.7738869"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3331526"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/HiPC.2019.00037"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/2723372.2742797"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/2213836.2213934"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2014.87"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/2391229.2391242"},{"key":"ref46","first-page":"29","article-title":"TritonSort: A balanced Large-Scale sorting system","volume-title":"Proc. 8th USENIX Symp. Networked Syst. Des. Implementation","author":"Rasmussen","year":"2011"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/781027.781052"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/BigData62323.2024.10825421"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3065737"}],"container-title":["IEEE Transactions on Big Data"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6687317\/11433832\/11277383.pdf?arnumber=11277383","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T20:16:44Z","timestamp":1773692204000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11277383\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":49,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tbdata.2025.3640011","relation":{},"ISSN":["2332-7790","2372-2096"],"issn-type":[{"value":"2332-7790","type":"electronic"},{"value":"2372-2096","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]}}}