{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T16:21:20Z","timestamp":1781972480664,"version":"3.54.5"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput."],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/tc.2022.3208206","type":"journal-article","created":{"date-parts":[[2022,9,20]],"date-time":"2022-09-20T19:31:00Z","timestamp":1663702260000},"page":"1-14","source":"Crossref","is-referenced-by-count":32,"title":["Dynamic Sparse Attention for Scalable Transformer Acceleration"],"prefix":"10.1109","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0792-8146","authenticated-orcid":false,"given":"Liu","family":"Liu","sequence":"first","affiliation":[{"name":"University of California, Santa Barbara, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6574-0649","authenticated-orcid":false,"given":"Zheng","family":"Qu","sequence":"additional","affiliation":[{"name":"University of California, Santa Barbara, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9601-4586","authenticated-orcid":false,"given":"Zhaodong","family":"Chen","sequence":"additional","affiliation":[{"name":"University of California, Santa Barbara, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2228-8829","authenticated-orcid":false,"given":"Fengbin","family":"Tu","sequence":"additional","affiliation":[{"name":"University of California, Santa Barbara, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8716-5793","authenticated-orcid":false,"given":"Yufei","family":"Ding","sequence":"additional","affiliation":[{"name":"University of California, Santa Barbara, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2093-1788","authenticated-orcid":false,"given":"Yuan","family":"Xie","sequence":"additional","affiliation":[{"name":"University of California, Santa Barbara, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"142","article-title":"Learning word vectors for sentiment analysis","author":"maas","year":"2011","journal-title":"Proc 49th Annu Meeting Assoc Comput Linguistics Hum Lang Technol"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00071"},{"key":"ref33","first-page":"5156","article-title":"Transformers are RNNs: Fast autoregressive transformers with linear attention","author":"katharopoulos","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref32","first-page":"9895","article-title":"Sparse is enough in scaling transformers","author":"jaszczur","year":"2021","journal-title":"Proc Adv Neural Informat Process Syst"},{"key":"ref31","article-title":"Efficient transformers: A survey","author":"tay","year":"2020","journal-title":"ACM Comput Surv"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00066"},{"key":"ref37","article-title":"Efficient 8-bit quantization of transformer neural machine language translation model","author":"bhandare","year":"2019"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00018"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3307650.3322214"},{"key":"ref34","article-title":"Random feature attention","author":"peng","year":"2021","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref10","article-title":"Generating long sequences with sparse transformers","author":"child","year":"2019"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-012-9211-2"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.232"},{"key":"ref12","article-title":"Longformer: The long-document transformer","author":"beltagy","year":"2020"},{"key":"ref13","article-title":"Big bird: Transformers for longer sequences","author":"zaheer","year":"2020"},{"key":"ref14","first-page":"9438","article-title":"Sparse sinkhorn attention","author":"tay","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref15","first-page":"328","article-title":"A$\\hat{3}$3^: Accelerating attention mechanisms in neural networks with approximation","author":"ham","year":"2020","journal-title":"Proc IEEE Int Symp High Perform Comput Archit"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00060"},{"key":"ref17","article-title":"Sparsebert: Rethinking the importance analysis in self-attention","author":"shi","year":"2021"},{"key":"ref18","article-title":"Long range arena: A benchmark for efficient transformers","volume":"abs 2011 4006","author":"tay","year":"2020","journal-title":"CoRR"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1223"},{"key":"ref28","article-title":"Linformer: Self-attention with linear complexity","author":"wang","year":"2020"},{"key":"ref4","first-page":"4055","article-title":"Image transformer","author":"parmar","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref27","article-title":"Rethinking attention with performers","author":"choromanski","year":"2021"},{"key":"ref3","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"Proc Conf North Amer Chapter Assoc Comput Linguistics Hum Lang Technol"},{"key":"ref6","first-page":"2337","article-title":"Efficient training of BERT by progressively stacking","author":"gong","year":"2019","journal-title":"Proc 36th Int Conf Mach Learn"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00069"},{"key":"ref5","article-title":"Language models are few-shot learners","author":"brown","year":"2020"},{"key":"ref8","article-title":"Reformer: The efficient transformer","author":"kitaev","year":"2020","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6301"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00353"},{"key":"ref1","first-page":"6000","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref20","article-title":"Hopfield networks is all you need","author":"ramsauer","year":"2020"},{"key":"ref45","article-title":"Pointer sentinel mixture models","author":"merity","year":"2016"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00075"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.363"},{"key":"ref42","article-title":"Long range arena: A benchmark for efficient transformers","author":"tay","year":"2021","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00021"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1264"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476182"},{"key":"ref44","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"radford","year":"2019","journal-title":"OpenAIRE blog"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00021"},{"key":"ref43","first-page":"142","article-title":"Learning word vectors for sentiment analysis","author":"maas","year":"2011","journal-title":"Proc 49th Annu Meeting Assoc Comput Linguistics Hum Lang Technol"},{"key":"ref25","article-title":"Cusparse library","author":"naumov","year":"2010","journal-title":"Proc GPU Technol Conf"}],"container-title":["IEEE Transactions on Computers"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/12\/4358213\/09896137.pdf?arnumber=9896137","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,17]],"date-time":"2022-11-17T16:40:46Z","timestamp":1668703246000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9896137\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/tc.2022.3208206","relation":{},"ISSN":["0018-9340","1557-9956","2326-3814"],"issn-type":[{"value":"0018-9340","type":"print"},{"value":"1557-9956","type":"electronic"},{"value":"2326-3814","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}