{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T06:56:30Z","timestamp":1781679390755,"version":"3.54.5"},"reference-count":56,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.neucom.2026.134015","type":"journal-article","created":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T06:52:38Z","timestamp":1779173558000},"page":"134015","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Adapting to dissimilar tasks for continual learning via gradient norm regularisation"],"prefix":"10.1016","volume":"695","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7385-4926","authenticated-orcid":false,"given":"Xulong","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Menghui","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhipeng","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Po","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neucom.2026.134015_bib0005","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","first-page":"139","article-title":"Memory aware synapses: learning what (not) to forget","author":"Aljundi","year":"2018"},{"key":"10.1016\/j.neucom.2026.134015_bib0010","first-page":"21428","article-title":"Geometric dataset distances via optimal transport","volume":"33","author":"Alvarez-Melis","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134015_bib0015","first-page":"15920","article-title":"Dark experience for general continual learning: a strong, simple baseline","volume":"33","author":"Buzzega","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134015_bib0020","series-title":"7th International Conference on Learning Representations, ICLR 2019","article-title":"Efficient lifelong learning with A-GEM","author":"Chaudhry","year":"2019"},{"key":"10.1016\/j.neucom.2026.134015_bib0025","first-page":"17466","article-title":"Mitigating forgetting in online continual learning via instance-aware parameterization","volume":"33","author":"Chen","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134015_bib0030","author":"Chen"},{"key":"10.1016\/j.neucom.2026.134015_bib0035","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"4109","article-title":"Large scale fine-grained categorization and domain-specific transfer learning","author":"Cui","year":"2018"},{"key":"10.1016\/j.neucom.2026.134015_bib0040","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1016\/j.neunet.2022.10.030","article-title":"Efficient perturbation inference and expandable network for continual learning","volume":"159","author":"Du","year":"2023","journal-title":"Neural Netw."},{"key":"10.1016\/j.neucom.2026.134015_bib0045","series-title":"International Conference on Artificial Intelligence and Statistics","first-page":"3762","article-title":"Orthogonal gradient descent for continual learning","author":"Farajtabar","year":"2020"},{"key":"10.1016\/j.neucom.2026.134015_bib0050","series-title":"International Conference on Learning Representations","article-title":"Sharpness-aware minimization for efficiently improving generalization","author":"Foret","year":"2020"},{"key":"10.1016\/j.neucom.2026.134015_bib0055","doi-asserted-by":"crossref","first-page":"369","DOI":"10.1016\/j.neunet.2023.03.006","article-title":"Generative negative replay for continual learning","volume":"162","author":"Graffieti","year":"2023","journal-title":"Neural Netw."},{"key":"10.1016\/j.neucom.2026.134015_bib0060","series-title":"The Thirty-Eighth Annual Conference on Neural Information Processing Systems","article-title":"Disentangling and mitigating the impact of task similarity for continual learning","author":"Hiratani","year":"2024"},{"key":"10.1016\/j.neucom.2026.134015_bib0065","series-title":"International Conference on Machine Learning","first-page":"754","article-title":"An efficient approach for assessing hyperparameter importance","author":"Hutter","year":"2014"},{"key":"10.1016\/j.neucom.2026.134015_bib0070","series-title":"European Conference on Computer Vision","first-page":"519","article-title":"Helpful or harmful: inter-task association in continual learning","author":"Jin","year":"2022"},{"key":"10.1016\/j.neucom.2026.134015_bib0075","first-page":"18493","article-title":"Continual learning of a mixed sequence of similar and dissimilar tasks","volume":"33","author":"Ke","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134015_bib0080","series-title":"The 2023 Conference on Empirical Methods in Natural Language Processing","article-title":"Sub-network discovery and soft-masking for continual learning of mixed tasks","author":"Ke","year":"2023"},{"key":"10.1016\/j.neucom.2026.134015_bib0085","doi-asserted-by":"crossref","first-page":"3521","DOI":"10.1073\/pnas.1611835114","article-title":"Overcoming catastrophic forgetting in neural networks","volume":"114","author":"Kirkpatrick","year":"2017","journal-title":"Proc. Natl. Acad. Sci."},{"key":"10.1016\/j.neucom.2026.134015_bib0090","series-title":"International Conference on Machine Learning","first-page":"17492","article-title":"Parameter-level soft-masking for continual learning","author":"Konishi","year":"2023"},{"key":"10.1016\/j.neucom.2026.134015_bib0095","series-title":"International Conference on Machine Learning","first-page":"3519","article-title":"Similarity of neural network representations revisited","author":"Kornblith","year":"2019"},{"key":"10.1016\/j.neucom.2026.134015_bib0100","series-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"10.1016\/j.neucom.2026.134015_bib0105","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"Krizhevsky","year":"2012","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134015_bib0110","series-title":"International Conference on Machine Learning","first-page":"6109","article-title":"Continual learning in the teacher-student setup: impact of task similarity","author":"Lee","year":"2021"},{"key":"10.1016\/j.neucom.2026.134015_bib0115","series-title":"International Conference on Machine Learning","first-page":"12455","article-title":"Maslow\u2019s hammer in catastrophic forgetting: node re-use vs. node activation","author":"Lee","year":"2022"},{"key":"10.1016\/j.neucom.2026.134015_bib0120","series-title":"International Conference on Machine Learning","first-page":"3925","article-title":"Learn to grow: a continual structure learning framework for overcoming catastrophic forgetting","author":"Li","year":"2019"},{"key":"10.1016\/j.neucom.2026.134015_bib0125","doi-asserted-by":"crossref","first-page":"2935","DOI":"10.1109\/TPAMI.2017.2773081","article-title":"Learning without forgetting","volume":"40","author":"Li","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.neucom.2026.134015_bib0130","series-title":"The Tenth International Conference on Learning Representations","article-title":"TRGP: trust region gradient projection for continual learning","author":"Lin","year":"2022"},{"key":"10.1016\/j.neucom.2026.134015_bib0135","series-title":"Proceedings of the 32nd ACM International Conference on Information and Knowledge Management","first-page":"1587","article-title":"Weak regression enhanced lifelong learning for improved performance and reduced training data","author":"Liu","year":"2023"},{"issue":"9","key":"10.1016\/j.neucom.2026.134015_bib0140","doi-asserted-by":"crossref","DOI":"10.1109\/TKDE.2024.3372462","article-title":"Unsupervised transfer aided lifelong regression for learning new tasks without target output","volume":"36","author":"Liu","year":"2024","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"10.1016\/j.neucom.2026.134015_bib0145","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"3600","article-title":"Avalanche: an end-to-end library for continual learning","author":"Lomonaco","year":"2021"},{"key":"10.1016\/j.neucom.2026.134015_bib0150","series-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems","first-page":"6470","article-title":"Gradient episodic memory for continual learning","author":"Lopez-Paz","year":"2017"},{"key":"10.1016\/j.neucom.2026.134015_bib0155","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","first-page":"67","article-title":"Piggyback: adapting a single network to multiple tasks by learning to mask weights","author":"Mallya","year":"2018"},{"key":"10.1016\/j.neucom.2026.134015_bib0160","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"7765","article-title":"Packnet: adding multiple tasks to a single network by iterative pruning","author":"Mallya","year":"2018"},{"key":"10.1016\/j.neucom.2026.134015_bib0165","series-title":"Conference on Lifelong Learning Agents","first-page":"366","article-title":"Tag: task-based accumulated gradients for lifelong learning","author":"Malviya","year":"2022"},{"key":"10.1016\/j.neucom.2026.134015_bib0170","series-title":"Affect and Cognition","first-page":"3","article-title":"The structure of value: accounting for taste","author":"Mandler","year":"2014"},{"key":"10.1016\/j.neucom.2026.134015_bib0175","series-title":"The Ninth International Conference on Learning Representations (ICLR 2022)","article-title":"Linear mode connectivity in multitask and continual learning","author":"Mirzadeh","year":"2021"},{"key":"10.1016\/j.neucom.2026.134015_bib0180","first-page":"7308","article-title":"Understanding the role of training regimes in continual learning","volume":"33","author":"Mirzadeh","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134015_bib0185","author":"Nguyen"},{"key":"10.1016\/j.neucom.2026.134015_bib0190","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1016\/j.neunet.2019.01.012","article-title":"Continual lifelong learning with neural networks: a review","volume":"113","author":"Parisi","year":"2019","journal-title":"Neural Netw."},{"key":"10.1016\/j.neucom.2026.134015_bib0195","series-title":"International Conference on Learning Representations","article-title":"Anatomy of catastrophic forgetting: hidden representations and task semantics","author":"Ramasesh","year":"2020"},{"key":"10.1016\/j.neucom.2026.134015_bib0200","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"2001","article-title":"icarl: incremental classifier and representation learning","author":"Rebuffi","year":"2017"},{"key":"10.1016\/j.neucom.2026.134015_bib0205","series-title":"International Conference on Learning Representations","article-title":"Learning to learn without forgetting by maximizing transfer and minimizing interference","author":"Riemer","year":"2018"},{"key":"10.1016\/j.neucom.2026.134015_bib0210","series-title":"International Conference on Learning Representations","article-title":"Gradient projection memory for continual learning","author":"Saha","year":"2020"},{"key":"10.1016\/j.neucom.2026.134015_bib0215","series-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems","first-page":"2994","article-title":"Continual learning with deep generative replay","author":"Shin","year":"2017"},{"key":"10.1016\/j.neucom.2026.134015_bib0220","author":"Sodhani"},{"key":"10.1016\/j.neucom.2026.134015_bib0225","first-page":"1","article-title":"Three types of incremental learning","author":"van de Ven","year":"2022","journal-title":"Nat. Mach. Intell."},{"key":"10.1016\/j.neucom.2026.134015_bib0230","doi-asserted-by":"crossref","first-page":"168","DOI":"10.1016\/j.patrec.2025.07.018","article-title":"SPOT: an efficient training-free task similarity quantification method for continual learning","volume":"197","author":"Wang","year":"2025","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.neucom.2026.134015_bib0235","series-title":"The Twelfth International Conference on Learning Representations","article-title":"A unified and general framework for continual learning","author":"Wang","year":"2024"},{"issue":"6","key":"10.1016\/j.neucom.2026.134015_bib0240","doi-asserted-by":"crossref","DOI":"10.1109\/TAI.2023.3339091","article-title":"Continual learning: a review of techniques, challenges and future directions","volume":"5","author":"Wickramasinghe","year":"2023","journal-title":"IEEE Trans. Artif. Intell."},{"key":"10.1016\/j.neucom.2026.134015_bib0245","series-title":"Tiny imagenet challenge","author":"Wu","year":"2017"},{"key":"10.1016\/j.neucom.2026.134015_bib0250","series-title":"IEEE CVPR","first-page":"8787","article-title":"IP102: a large-scale benchmark dataset for insect Pest recognition","author":"Wu","year":"2019"},{"key":"10.1016\/j.neucom.2026.134015_bib0255","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"8787","article-title":"IP102: a large-scale benchmark dataset for insect Pest recognition","author":"Wu","year":"2019"},{"key":"10.1016\/j.neucom.2026.134015_bib0260","doi-asserted-by":"crossref","first-page":"146","DOI":"10.1016\/j.neunet.2023.03.025","article-title":"Online continual learning with declarative memory","volume":"163","author":"Xiao","year":"2023","journal-title":"Neural Netw."},{"key":"10.1016\/j.neucom.2026.134015_bib0265","series-title":"6th International Conference on Learning Representations, ICLR 2018","article-title":"Lifelong learning with dynamically expandable networks","author":"Yoon","year":"2018"},{"key":"10.1016\/j.neucom.2026.134015_bib0270","series-title":"International Conference on Machine Learning","first-page":"3987","article-title":"Continual learning through synaptic intelligence","author":"Zenke","year":"2017"},{"key":"10.1016\/j.neucom.2026.134015_bib0275","series-title":"International Conference on Learning Representations","article-title":"mixup: beyond empirical risk minimization","author":"Zhang","year":"2018"},{"key":"10.1016\/j.neucom.2026.134015_bib0280","series-title":"International Conference on Machine Learning","first-page":"26982","article-title":"Penalizing gradient norm for efficiently improving generalization in deep learning","author":"Zhao","year":"2022"}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S092523122601413X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S092523122601413X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T06:33:45Z","timestamp":1781678025000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S092523122601413X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":56,"alternative-id":["S092523122601413X"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134015","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Adapting to dissimilar tasks for continual learning via gradient norm regularisation","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134015","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"134015"}}