{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:34:01Z","timestamp":1763192041463,"version":"3.45.0"},"reference-count":43,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11227313","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-9","source":"Crossref","is-referenced-by-count":0,"title":["Remembering Transformer for Continual Learning"],"prefix":"10.1109","author":[{"given":"Yuwei","family":"Sun","sequence":"first","affiliation":[{"name":"Araya Research"}]},{"given":"Ippei","family":"Fujisawa","sequence":"additional","affiliation":[{"name":"Araya Research"}]},{"given":"Arthur","family":"Juliani","sequence":"additional","affiliation":[{"name":"Microsoft Research"}]},{"given":"Jun","family":"Sakuma","sequence":"additional","affiliation":[{"name":"RIKEN AIP"}]},{"given":"Ryota","family":"Kanai","sequence":"additional","affiliation":[{"name":"Araya Research"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.79"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00422"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.753"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1126\/science.287.5451.248"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2016.05.004"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.neulet.2018.01.053"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-31775-6"},{"article-title":"Distilling the knowledge in a neural network","year":"2015","author":"Hinton","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.587"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM54844.2022.00154"},{"article-title":"Continual learning with tiny episodic memories","volume-title":"Workshop on Multi-Task and Lifelong Reinforcement Learning","author":"Chaudhry","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-020-17866-2"},{"article-title":"Overcoming catastrophic forgetting for continual learning via model adaptation","volume-title":"ICLR","author":"Hu","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00390"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-019-0080-x"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00581"},{"key":"ref17","first-page":"14306","article-title":"Class-incremental learning via dual augmentation","volume-title":"NeurIPS","author":"Zhu"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"ref19","first-page":"4528","article-title":"Progress & compress: A scalable framework for continual learning","volume-title":"International Conference on machine learning","author":"Schwarz"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01226"},{"key":"ref21","first-page":"532","article-title":"Riemannian walk for incremental learning: Under-standing forgetting and intransigence","volume-title":"Proceedings of the European conference on computer vision (ECCV)","author":"Chaudhry"},{"key":"ref22","article-title":"Uncertainty-based continual learning with adaptive regularization","volume-title":"Advances in neural information processing systems","volume":"32","author":"Ahn"},{"article-title":"Super-masks in superposition","volume-title":"NeurIPS","author":"Wortsman","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00431"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.753"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00908"},{"article-title":"Dark experience for general continual learning: a strong, simple baseline","volume-title":"NeurIPS","author":"Buzzega","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02191"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2020.00019"},{"article-title":"Continual learning with hypernetworks","volume-title":"ICLR","author":"von Oswald","key":"ref30"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00024"},{"article-title":"Scaling vision with sparse mixture of experts","volume-title":"NeurIPS","author":"Riquelme","key":"ref32"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"ICLR","author":"Dosovitskiy","key":"ref33"},{"article-title":"Sparse moes meet efficient ensembles","year":"2021","author":"Allingham","key":"ref34"},{"article-title":"Lora: Low-rank adaptation of large language models","year":"2021","author":"Hu","key":"ref35"},{"article-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer","year":"2017","author":"Shazeer","key":"ref36"},{"article-title":"Routing networks and the challenges of modular and compositional computation","year":"2019","author":"Rosenbaum","key":"ref37"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553517"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.587"},{"article-title":"Learning multiple layers of features from tiny images","year":"2009","author":"Krizhevsky","key":"ref40"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58574-7_42"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2773081"},{"key":"ref43","first-page":"923","article-title":"I2i: Initializing adapters with improvised knowledge","volume-title":"Conference on Lifelong Learning Agents","author":"Srinivasan"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2025,6,30]]},"location":"Rome, Italy","end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11227313.pdf?arnumber=11227313","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:31:57Z","timestamp":1763191917000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11227313\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11227313","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}