{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T05:31:00Z","timestamp":1781587860853,"version":"3.54.5"},"reference-count":81,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62032013"],"award-info":[{"award-number":["62032013"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and technology projects in Liaoning Province","award":["2023JH3\/10200005"],"award-info":[{"award-number":["2023JH3\/10200005"]}]},{"name":"Natural Science Foundation","award":["JCYJ20241202124430041"],"award-info":[{"award-number":["JCYJ20241202124430041"]}]},{"DOI":"10.13039\/501100001381","name":"National Research Foundation Singapore","doi-asserted-by":"publisher","award":["NRF-P2024-001"],"award-info":[{"award-number":["NRF-P2024-001"]}],"id":[{"id":"10.13039\/501100001381","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1109\/tpami.2025.3539019","type":"journal-article","created":{"date-parts":[[2025,2,5]],"date-time":"2025-02-05T18:51:30Z","timestamp":1738781490000},"page":"3895-3907","source":"Crossref","is-referenced-by-count":3,"title":["Revisiting Flatness-Aware Optimization in Continual Learning With Orthogonal Gradient Projection"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5419-5286","authenticated-orcid":false,"given":"Enneng","family":"Yang","sequence":"first","affiliation":[{"name":"Northeastern University, Shenyang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5659-3464","authenticated-orcid":false,"given":"Li","family":"Shen","sequence":"additional","affiliation":[{"name":"Shenzhen Campus of Sun Yat-sen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2780-9446","authenticated-orcid":false,"given":"Zhenyi","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Maryland, College Park, MD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shiwei","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Oxford, Oxford, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1709-5056","authenticated-orcid":false,"given":"Guibing","family":"Guo","sequence":"additional","affiliation":[{"name":"Northeastern University, Shenyang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xingwei","family":"Wang","sequence":"additional","affiliation":[{"name":"Northeastern University, Shenyang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7225-5449","authenticated-orcid":false,"given":"Dacheng","family":"Tao","sequence":"additional","affiliation":[{"name":"College of Computing and Data Science, Nanyang Technological University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.01.012"},{"key":"ref2","article-title":"An introduction to lifelong supervised learning","author":"Sodhani","year":"2022"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3429383"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3367329"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1037\/0033-295x.97.2.285"},{"key":"ref6","first-page":"1176","article-title":"Catastrophic interference in connectionist networks: Can it be predicted, can it be prevented?","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"French"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00747-w"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3498346"},{"key":"ref9","article-title":"Continual learning with tiny episodic memories","author":"Chaudhry","year":"2019"},{"key":"ref10","first-page":"2990","article-title":"Continual learning with deep generative replay","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Shin"},{"key":"ref11","first-page":"22 985","article-title":"Improving task-free continual learning by distributionally robust memory evolution","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref12","first-page":"4555","article-title":"Overcoming catastrophic forgetting with hard attention to the task","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Serr\u00e0"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00810"},{"key":"ref14","article-title":"Progressive neural networks","author":"Rusu","year":"2016"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"ref16","first-page":"3987","article-title":"Continual learning through synaptic intelligence","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zenke"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_33"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-019-0080-x"},{"key":"ref19","first-page":"3762","article-title":"Orthogonal gradient descent for continual learning","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Farajtabar"},{"key":"ref20","first-page":"1","article-title":"TRGP: Trust region gradient projection for continual learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lin"},{"key":"ref21","first-page":"1","article-title":"Gradient projection memory for continual learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Saha"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2023.08.010"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i8.26157"},{"key":"ref24","first-page":"9900","article-title":"Continual learning in low-rank orthogonal subspaces","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Chaudhry"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00362"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.1.1"},{"key":"ref27","volume-title":"Statistical Learning Theory","author":"Vapnik","year":"1998"},{"key":"ref28","first-page":"18 710","article-title":"Flattening sharpness for dynamic gradient projection memory benefits continual learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Deng"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00755"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00025"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548054"},{"key":"ref32","first-page":"1","article-title":"Sharpness-aware minimization for efficiently improving generalization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Foret"},{"key":"ref33","first-page":"1","article-title":"On large-batch training for deep learning: Generalization gap and sharp minima","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Keskar"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01204"},{"key":"ref35","first-page":"1","article-title":"Surrogate gap minimization improves sharpness-aware training","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhuang"},{"key":"ref36","first-page":"30 950","article-title":"Make sharpness-aware minimization stronger: A sparsified perturbation approach","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Mi"},{"key":"ref37","first-page":"1","article-title":"Mixup: Beyond empirical risk minimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang"},{"key":"ref38","first-page":"1","article-title":"How does mixup help with robustness and generalization?","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_9"},{"key":"ref40","first-page":"1","article-title":"Efficient lifelong learning with A-GEM","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chaudhry"},{"key":"ref41","first-page":"1","article-title":"CPR: Classifier-projection regularization for continual learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Cha"},{"key":"ref42","first-page":"11817","article-title":"Gradient based sample selection for online continual learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Aljundi"},{"key":"ref43","first-page":"1","article-title":"Online continual learning on class incremental blurry task configuration with anytime inference","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Koh"},{"key":"ref44","first-page":"1","article-title":"Learning to learn without forgetting by maximizing transfer and minimizing interference","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Riemer"},{"key":"ref45","first-page":"1","article-title":"Memory replay with data compression for continual learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang"},{"key":"ref46","first-page":"1","article-title":"A unified and general framework for continual learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang"},{"key":"ref47","first-page":"6470","article-title":"Gradient episodic memory for continual learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lopez-Paz"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.587"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00812"},{"key":"ref50","first-page":"5966","article-title":"Memory replay GANs: Learning to generate images from new categories without forgetting","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Chenshen"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00672"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01226"},{"key":"ref53","first-page":"34391","article-title":"Remember the past: Distilling datasets into addressable memories for neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Deng"},{"key":"ref54","first-page":"67625","article-title":"An efficient dataset condensation plugin and its application to continual learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2773081"},{"key":"ref56","first-page":"1","article-title":"Representational continuity for unsupervised continual learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Madaan"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00528"},{"key":"ref58","first-page":"1","article-title":"Continual learning with filter atom swapping","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Miao"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.753"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01141"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00518"},{"key":"ref62","first-page":"639","article-title":"Towards understanding sharpness-aware minimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Andriushchenko"},{"key":"ref63","first-page":"876","article-title":"Averaging weights leads to wider optima and better generalization","volume-title":"Proc. Conf. Uncertainty Artif. Intell.","author":"Izmailov"},{"key":"ref64","first-page":"23 965","article-title":"Model soups: Averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wortsman"},{"key":"ref65","first-page":"7308","article-title":"Understanding the role of training regimes in continual learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Mirzadeh"},{"issue":"214","key":"ref66","first-page":"1","article-title":"An empirical investigation of the role of pre-training in lifelong learning","volume":"24","author":"Mehta","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"ref67","first-page":"1","article-title":"Regularizing neural networks by penalizing confident output distributions","volume-title":"Proc. Int. Conf. Learn. Representations Workshop Track","author":"Pereyra"},{"key":"ref68","first-page":"6747","article-title":"Overcoming catastrophic forgetting in incremental few-shot learning by finding flat minima","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Shi"},{"key":"ref69","first-page":"2958","article-title":"Adversarial weight perturbation helps robust generalization","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wu"},{"key":"ref70","first-page":"6467","article-title":"Gradient episodic memory for continual learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lopez-Paz"},{"key":"ref71","first-page":"1","article-title":"Uncertainty-guided continual learning with Bayesian neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ebrahimi"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_23"},{"issue":"2","key":"ref73","first-page":"2","article-title":"Reading digits in natural images with unsupervised feature learning","volume":"2011","author":"Netzer","year":"2011","journal-title":"NIPS Workshop Deep Learn Unsupervised Feature Learn."},{"key":"ref74","article-title":"Notmnist dataset","author":"Bulatov","year":"2011"},{"key":"ref75","article-title":"Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms","author":"Xiao","year":"2017"},{"key":"ref76","first-page":"3637","article-title":"Matching networks for one shot learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Vinyals"},{"key":"ref77","first-page":"1106","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Krizhevsky"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref79","first-page":"1","article-title":"Explaining and harnessing adversarial examples","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Goodfellow"},{"key":"ref80","first-page":"1","article-title":"Efficient sharpness-aware minimization for improved training of neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Du"},{"key":"ref81","first-page":"23 439","article-title":"Sharpness-aware training for free","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Du"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10958761\/10874188.pdf?arnumber=10874188","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,10]],"date-time":"2025-04-10T17:13:52Z","timestamp":1744305232000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10874188\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5]]},"references-count":81,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3539019","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":[[2025,5]]}}}