{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T20:22:25Z","timestamp":1740169345989,"version":"3.37.3"},"reference-count":25,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100014188","name":"Ministry of Science and ICT (MSIT), South Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010418","name":"Institute for Information and Communications Technology Planning and Evaluation","doi-asserted-by":"publisher","award":["RS-2024-00259099"],"award-info":[{"award-number":["RS-2024-00259099"]}],"id":[{"id":"10.13039\/501100010418","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Korean Government","award":["NRF-2022R1G1A1013586","NRF-RS-2024-00359076"],"award-info":[{"award-number":["NRF-2022R1G1A1013586","NRF-RS-2024-00359076"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3425638","type":"journal-article","created":{"date-parts":[[2024,7,9]],"date-time":"2024-07-09T18:48:56Z","timestamp":1720550936000},"page":"131373-131384","source":"Crossref","is-referenced-by-count":0,"title":["Exploring Attention Sparsity to Accelerate Transformer Training on GPUs"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-0175-0753","authenticated-orcid":false,"given":"Bokyeong","family":"Yoon","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, Sogang University, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ah-Hyun","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Sogang University, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3751-8869","authenticated-orcid":false,"given":"Jinsung","family":"Kim","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Chung-Ang University, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4992-6181","authenticated-orcid":false,"given":"Gordon Euhyun","family":"Moon","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Sogang University, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"issue":"2","key":"ref2","first-page":"711","article-title":"Data movement is all you need: A case study on optimizing transformers","volume":"3","author":"Ivanov","year":"2021","journal-title":"Proc. Mach. Learn. Syst."},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-2253-2_13"},{"key":"ref4","first-page":"17283","article-title":"Big Bird: Transformers for longer sequences","volume-title":"Proc. 34th Conf. Neural Inf. Process. Syst.","author":"Zaheer"},{"key":"ref5","article-title":"Longformer: The long-document transformer","author":"Beltagy","year":"2020","journal-title":"arXiv:2004.05150"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00353"},{"key":"ref7","first-page":"12437","article-title":"Poolingformer: Long document modeling with pooling attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref8","article-title":"Linformer: Self-attention with linear complexity","author":"Wang","year":"2020","journal-title":"arXiv:2006.04768"},{"key":"ref9","first-page":"1","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics","author":"Devlin"},{"key":"ref10","first-page":"1","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Dosovitskiy"},{"key":"ref11","article-title":"Generating long sequences with sparse transformers","author":"Child","year":"2019","journal-title":"arXiv:1904.10509"},{"key":"ref12","first-page":"1","article-title":"Reformer: The efficient transformer","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kitaev"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.19"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-33374-3_35"},{"key":"ref15","first-page":"12098","article-title":"Longcoder: A long-range pre-trained language model for code completion","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xu"},{"key":"ref16","first-page":"1","article-title":"Imagenet-21K pretraining for the masses","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst. Datasets Benchmarks Track","author":"Ridnik"},{"volume-title":"Wikimedia Downloads","year":"2024","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.11"},{"volume-title":"Learning Multiple Layers of Features From Tiny Images","year":"2009","author":"Krizhevsky","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5446"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref22","first-page":"1","article-title":"AlBERT: A lite BERT for self-supervised learning of language representations","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Lan"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3017994"},{"key":"ref24","first-page":"1","article-title":"Character-level convolutional networks for text classification","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"volume-title":"INaturalist Competition Dataset","year":"2018","key":"ref25"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10380310\/10589623.pdf?arnumber=10589623","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,25]],"date-time":"2024-09-25T04:54:32Z","timestamp":1727240072000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10589623\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3425638","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2024]]}}}