{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T16:43:11Z","timestamp":1778085791932,"version":"3.51.4"},"reference-count":79,"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. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/tpami.2022.3218265","type":"journal-article","created":{"date-parts":[[2022,11,4]],"date-time":"2022-11-04T01:18:53Z","timestamp":1667524733000},"page":"1-12","source":"Crossref","is-referenced-by-count":8,"title":["Drinking from a Firehose: Continual Learning with Web-scale Natural Language"],"prefix":"10.1109","author":[{"given":"Hexiang","family":"Hu","sequence":"first","affiliation":[{"name":"Department of Computer Science, Viterbi School of Engineering, University of Southern California, Los Angeles, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1542-7547","authenticated-orcid":false,"given":"Ozan","family":"Sener","sequence":"additional","affiliation":[{"name":"Intel Labs, Santa Clara, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fei","family":"Sha","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Viterbi School of Engineering, University of Southern California, Los Angeles, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0858-0970","authenticated-orcid":false,"given":"Vladlen","family":"Koltun","sequence":"additional","affiliation":[{"name":"Intel Labs, Santa Clara, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"640","article-title":"Is learning the n-th thing any easier than learning the first?","volume-title":"Proc. 8th Int. Conf. Neural Inf. Process. Syst.","author":"Thrun"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-01581-6"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-009-7758-7"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.01.012"},{"key":"ref6","article-title":"Continual learning: A comparative study on how to defy forgetting in classification tasks","author":"Lange","year":"2019"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.574"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v24i1.7519"},{"key":"ref9","article-title":"Language models are unsupervised multitask learners","author":"Radford","year":"2019"},{"key":"ref10","article-title":"Language models are few-shot learners","author":"Brown","year":"2020"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/s0079-7421(08)60536-8"},{"key":"ref12","first-page":"3987","article-title":"Continual learning through synaptic intelligence","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Zenke"},{"key":"ref13","article-title":"Variational continual learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Nguyen"},{"key":"ref14","first-page":"3742","article-title":"Online structured laplace approximations for overcoming catastrophic forgetting","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Ritter"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_33"},{"key":"ref16","first-page":"4535","article-title":"Progress & compress: A scalable framework for continual learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schwarz"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01151"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093365"},{"key":"ref19","article-title":"Less-forgetting learning in deep neural networks","author":"Jung","year":"2016"},{"key":"ref20","first-page":"1329","article-title":"Encoder based lifelong learning","volume-title":"Proc. IEEE Int. Conf. Comput. Vis.","author":"Triki"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-47922-8_8"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.753"},{"key":"ref23","article-title":"Improving and understanding variational continual learning","author":"Swaroop","year":"2019"},{"key":"ref24","first-page":"4392","article-title":"Uncertainty-based continual learning with adaptive regularization","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Ahn"},{"key":"ref25","article-title":"Facilitating Bayesian continual learning by natural gradients and Stein gradients","author":"Chen","year":"2019"},{"key":"ref26","first-page":"2994","article-title":"Continual learning with deep generative replay","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Shin"},{"key":"ref27","first-page":"6470","article-title":"Gradient episodic memory for continual learning","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Lopez-Paz"},{"key":"ref28","article-title":"Efficient lifelong learning with A-GEM","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chaudhry"},{"key":"ref29","article-title":"Continual learning with tiny episodic memories","author":"Chaudhry","year":"2019"},{"key":"ref30","article-title":"Online continual learning with no task boundaries","author":"Aljundi","year":"2019"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11595"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.587"},{"key":"ref33","article-title":"Experience replay for continual learning","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Rolnick"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1080\/09540099550039318"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_31"},{"key":"ref36","article-title":"Dark experience for general continual learning: A strong, simple baseline","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Buzzega"},{"key":"ref37","article-title":"Progressive neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Rusu"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_37"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00810"},{"key":"ref40","first-page":"4548","article-title":"Overcoming catastrophic forgetting with hard attention to the task","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Serr\u00e0"},{"key":"ref41","article-title":"Gradient based sample selection for online continual learning","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Aljundi"},{"key":"ref42","article-title":"Continual learning of a mixed sequence of similar and dissimilar tasks","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Ke"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1561\/2200000018"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1561\/9781680831719"},{"key":"ref45","first-page":"1433","article-title":"Efficient regret minimization in non-convex games","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Hazan"},{"key":"ref46","first-page":"6000","article-title":"Attention is all you need","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Vaswani"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1206"},{"key":"ref48","first-page":"2965","article-title":"Multi-task learning for sequence tagging: An empirical study","volume-title":"Proc. 27th Int. Conf. Comput. Linguistics","author":"Changpinyo"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1441"},{"key":"ref50","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Houlsby"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/w18-5446"},{"key":"ref52","article-title":"SuperGLUE: A stickier benchmark for general-purpose language understanding systems","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref53","first-page":"506","article-title":"Learning multiple visual domains with residual adapters","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Rebuffi"},{"key":"ref54","first-page":"1587","article-title":"Toward controlled generation of text","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Hu"},{"key":"ref55","first-page":"6833","article-title":"Style transfer from non-parallel text by cross-alignment","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Shen"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-4912"},{"key":"ref57","first-page":"5108","article-title":"Content preserving text generation with attribute controls","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Logeswaran"},{"key":"ref58","article-title":"Multiple-attribute text rewriting","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lample"},{"key":"ref59","article-title":"Plug and play language models: A simple approach to controlled text generation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dathathri"},{"key":"ref60","article-title":"CTRL: A conditional transformer language model for controllable generation","author":"Keskar","year":"2019"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/219717.219745"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/1376616.1376746"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-76298-0_52"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/1242572.1242667"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2012.06.001"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.178"},{"key":"ref67","article-title":"RoboBrain: Large-scale knowledge engine for robots","author":"Saxena","year":"2014"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"ref69","article-title":"Googles neural machine translation system: Bridging the gap between human and machine translation","author":"Wu","year":"2016"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1007"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.158"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.590"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(96)00127-X"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/s00365-006-0663-2"},{"key":"ref76","article-title":"Learning to guide random search","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Sener"},{"key":"ref77","article-title":"On the convergence of SGD with biased gradients","author":"Ajalloeian","year":"2020"},{"key":"ref78","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma"},{"key":"ref79","article-title":"Gradient based sample selection","author":"Aljundi","year":"2013"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/4359286\/09933017.pdf?arnumber=9933017","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T22:53:36Z","timestamp":1705964016000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9933017\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":79,"URL":"https:\/\/doi.org\/10.1109\/tpami.2022.3218265","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}