{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,15]],"date-time":"2026-08-15T03:22:34Z","timestamp":1786764154491,"version":"build-2736575974"},"reference-count":182,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025,1]]},"DOI":"10.1109\/tpami.2024.3463709","type":"journal-article","created":{"date-parts":[[2024,9,18]],"date-time":"2024-09-18T17:56:25Z","timestamp":1726682185000},"page":"413-432","source":"Crossref","is-referenced-by-count":22,"title":["When Meta-Learning Meets Online and Continual Learning: A Survey"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-2726-1144","authenticated-orcid":false,"given":"Jaehyeon","family":"Son","sequence":"first","affiliation":[{"name":"Seoul National University, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1425-9262","authenticated-orcid":false,"given":"Soochan","family":"Lee","sequence":"additional","affiliation":[{"name":"LG AI Research, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9543-7453","authenticated-orcid":false,"given":"Gunhee","family":"Kim","sequence":"additional","affiliation":[{"name":"Seoul National University, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.04.112"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.01.012"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3057446"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3079209"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.5555\/3294996.3295163"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00131"},{"key":"ref7","article-title":"Meta-SGD: Learning to learn quickly for few shot learning","author":"Li","year":"2017"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_23"},{"key":"ref9","first-page":"3915","article-title":"Feature-critic networks for heterogeneous domain generalization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3357847"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1007\/978-3-030-05318-5_2","volume-title":"Automated Machine Learning","author":"Vanschoren","year":"2019"},{"key":"ref12","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref14","article-title":"Auto-encoding variational bayes","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma"},{"key":"ref15","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ho"},{"key":"ref16","first-page":"3603","article-title":"Implicit generation and modeling with energy based models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Du"},{"key":"ref17","first-page":"3987","article-title":"Continual learning through synaptic intelligence","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zenke"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref19","first-page":"3521","article-title":"Overcoming catastrophic forgetting in neural networks","volume-title":"Proc. Nat. Acad. Sci.","volume":"114","author":"Kirkpatrick","year":"2016"},{"key":"ref20","article-title":"Progress & compress: A scalable framework for continual learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schwarz"},{"key":"ref21","article-title":"Progressive neural networks","author":"Rusu","year":"2016"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.753"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01151"},{"key":"ref24","article-title":"A neural Dirichlet process mixture model for task-free continual learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lee"},{"key":"ref25","first-page":"6467","article-title":"Gradient episodic memory for continual learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lopez-Paz"},{"key":"ref26","article-title":"Don\u2019t forget, there is more than forgetting: New metrics for continual learning","author":"Rodr\u00edguez","year":"2018"},{"key":"ref27","volume-title":"Probably Approximately Correct: Nature\u2019s Algorithms for Learning and Prospering in a Complex World","author":"Valiant","year":"2013"},{"key":"ref28","first-page":"2568","article-title":"One shot learning of simple visual concepts","volume":"33","author":"Lake","year":"2011","journal-title":"Cogn. Sci."},{"key":"ref29","article-title":"Task agnostic continual learning via meta learning","volume-title":"Proc. 4th Lifelong Mach. Learn. Workshop Int. Conf. Mach. Learn.","author":"He"},{"key":"ref30","first-page":"2933","article-title":"Gradient-based meta-learning with learned layerwise metric and subspace","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lee"},{"key":"ref31","article-title":"Automated relational meta-learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yao"},{"key":"ref32","first-page":"3981","article-title":"Learning to learn by gradient descent by gradient descent","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Andrychowicz"},{"key":"ref33","article-title":"Learning to optimize","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li"},{"key":"ref34","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Finn"},{"key":"ref35","article-title":"How to train your MAML","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Antoniou"},{"key":"ref36","first-page":"113","article-title":"Meta-learning with implicit gradients","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Rajeswaran"},{"key":"ref37","article-title":"Meta-learning with warped gradient descent","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Flennerhag"},{"key":"ref38","first-page":"1723","article-title":"Truncated back-propagation for bilevel optimization","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Shaban"},{"key":"ref39","article-title":"Meta-learning with differentiable closed-form solvers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bertinetto"},{"key":"ref40","first-page":"9603","article-title":"Large-scale meta-learning with continual trajectory shifting","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Shin"},{"key":"ref41","article-title":"On first-order meta-learning algorithms","author":"Nichol","year":"2018"},{"key":"ref42","first-page":"7693","article-title":"Fast context adaptation via meta-learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zintgraf"},{"key":"ref43","first-page":"1818","article-title":"Meta-learning representations for continual learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Javed"},{"key":"ref44","article-title":"Rapid learning or feature reuse? Towards understanding the effectiveness of MAML","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Raghu"},{"key":"ref45","article-title":"Optimization as a model for few-shot learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ravi"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-44668-0_13"},{"key":"ref47","article-title":"A simple neural attentive meta-learner","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Mishra"},{"key":"ref48","first-page":"1842","article-title":"Meta-learning with memory-augmented neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Santoro"},{"key":"ref49","first-page":"2554","article-title":"Meta networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Munkhdalai"},{"key":"ref50","first-page":"1","article-title":"Siamese neural networks for one-shot image recognition","volume-title":"Proc. ICML Deep Learn. Workshop","author":"Koch"},{"key":"ref51","first-page":"3630","article-title":"Matching networks for one shot learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Vinyals"},{"key":"ref52","article-title":"Few-shot learning with graph neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Satorras"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.587"},{"key":"ref54","first-page":"348","article-title":"Experience replay for continual learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Rolnick"},{"key":"ref55","article-title":"Learning to learn without forgetting by maximizing transfer and minimizing interference","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Riemer"},{"key":"ref56","article-title":"Efficient lifelong learning with A-GEM","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chaudhry"},{"key":"ref57","first-page":"11816","article-title":"Gradient based sample selection for online continual learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Aljundi"},{"key":"ref58","first-page":"2990","article-title":"Continual learning with deep generative replay","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Shin"},{"key":"ref59","first-page":"1","article-title":"Generative models from the perspective of continual learning","volume-title":"Proc. Int. Joint Conf. Neural Netw.","author":"Lesort"},{"key":"ref60","article-title":"LAMOL: Language modeling for lifelong language learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Sun"},{"key":"ref61","article-title":"Incremental classifier learning with generative adversarial networks","author":"Wu","year":"2018"},{"key":"ref62","article-title":"Generative replay with feedback connections as a general strategy for continual learning","author":"van de Ven","year":"2018"},{"key":"ref63","article-title":"Lifelong learning with dynamically expandable networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yoon"},{"key":"ref64","article-title":"Learning to continually learn","author":"Beaulieu","year":"2020"},{"key":"ref65","article-title":"Continuous adaptation via meta-learning in nonstationary and competitive environments","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Al-Shedivat"},{"key":"ref66","first-page":"5541","article-title":"A policy gradient algorithm for learning to learn in multiagent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref67","first-page":"21592","article-title":"Generative vs. discriminative: Rethinking the meta-continual learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Banayeeanzade"},{"key":"ref68","first-page":"318","article-title":"Meta-learning priors for efficient online Bayesian regression","volume-title":"Proc. Workshop Algorithmic Found. Robot.","author":"Harrison"},{"key":"ref69","first-page":"26621","article-title":"Learning to continually learn with the Bayesian principle","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lee"},{"key":"ref70","first-page":"70433","article-title":"Recasting continual learning as sequence modeling","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lee"},{"key":"ref71","article-title":"RL2: Fast reinforcement learning via slow reinforcement learning","author":"Duan","year":"2016"},{"key":"ref72","article-title":"Learning to adapt in dynamic, real-world environments through meta-reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Nagabandi"},{"key":"ref73","first-page":"47016","article-title":"Structured state space models for in-context reinforcement learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref74","first-page":"1920","article-title":"Online meta-learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Finn"},{"key":"ref75","first-page":"32","article-title":"Memory efficient online meta learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Acar"},{"key":"ref76","first-page":"11909","article-title":"Addressing catastrophic forgetting in few-shot problems","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yap"},{"key":"ref77","first-page":"16532","article-title":"Online fast adaptation and knowledge accumulation (OSAKA): A new approach to continual learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Caccia"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.661"},{"key":"ref79","first-page":"9119","article-title":"Reconciling meta-learning and continual learning with online mixtures of tasks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Jerfel"},{"key":"ref80","article-title":"Deep online learning via meta-learning: Continual adaptation for model-based RL","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Nagabandi"},{"key":"ref81","first-page":"24556","article-title":"Variational continual Bayesian meta-learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref82","first-page":"6779","article-title":"Online structured meta-learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Yao"},{"key":"ref83","first-page":"37358","article-title":"Adaptive compositional continual meta-learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wu"},{"key":"ref84","first-page":"11588","article-title":"Look-ahead meta learning for continual learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Gupta"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01360"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00442"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3124133"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-4326"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.39"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17241"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.62"},{"key":"ref92","article-title":"Meta continual learning revisited: Implicitly enhancing online hessian approximation via variance reduction","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wu"},{"key":"ref93","article-title":"Continual learning with hypernetworks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"von Oswald"},{"key":"ref94","article-title":"Overcoming catastrophic forgetting for continual learning via model adaptation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu"},{"key":"ref95","first-page":"14374","article-title":"Meta-consolidation for continual learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Joseph"},{"key":"ref96","article-title":"Continual learning in recurrent neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ehret"},{"key":"ref97","first-page":"2338","article-title":"Continual learning with dependency preserving hypernetworks","volume-title":"Proc. Winter Conf. Appl. Comput. Vis.","author":"Chandra"},{"key":"ref98","first-page":"318","article-title":"Partial hypernetworks for continual learning","volume-title":"Proc. Conf. Lifelong Learn. Agents","author":"Hemati"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01220"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00256"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16213"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00884"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00854"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16334"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00885"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00673"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01227"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2022.12.024"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01139"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00748"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01377"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3200865"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01386"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/icra46639.2022.9811856"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25129"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3088545"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00883"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160283"},{"key":"ref119","article-title":"Meta-learning and universality: Deep representations and gradient descent can approximate any learning algorithm","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Finn"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_33"},{"key":"ref121","article-title":"Variational continual learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Nguyen"},{"key":"ref122","article-title":"A unifying Bayesian view of continual learning","author":"Farquhar","year":"2019"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1098\/rspa.1934.0050"},{"key":"ref124","article-title":"Sur les lois de probabilit\u00e9a estimation exhaustive","volume":"260","author":"Darmois","year":"1935","journal-title":"CR Acad. Sci. Paris"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1017\/S0305004100019307"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1090\/S0002-9947-1936-1501854-3"},{"key":"ref127","article-title":"Language models are few-shot learners","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Brown"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref129","first-page":"5156","article-title":"Transformers are RNNs: Fast autoregressive transformers with linear attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Katharopoulos"},{"key":"ref130","article-title":"Rethinking attention with performers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Choromanski"},{"issue":"6","key":"ref131","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3530811","article-title":"Efficient transformers: A survey","volume":"55","author":"Tay","year":"2020","journal-title":"ACM Comput. Surv."},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref133","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref134","first-page":"38546","article-title":"Exploring length generalization in large language models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Anil"},{"key":"ref135","article-title":"Train short, test long: Attention with linear biases enables input length extrapolation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Press"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-short.161"},{"key":"ref137","first-page":"13089","article-title":"Online-within-online meta-learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Denevi"},{"key":"ref138","first-page":"17571","article-title":"Continuous meta-learning without tasks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Harrison"},{"key":"ref139","article-title":"Wandering within a world: Online contextualized few-shot learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ren"},{"key":"ref140","first-page":"97","article-title":"Approximation to bayes risk in repeated play","volume":"3","author":"Hannan","year":"1957","journal-title":"Contributions Theory Games"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcss.2004.10.016"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511569920.017"},{"key":"ref143","first-page":"3742","article-title":"Online structured laplace approximations for overcoming catastrophic forgetting","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ritter"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-statistics-031017-100325"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1176342871"},{"key":"ref146","article-title":"Bayesian density estimation by mixtures of normal distributions","volume-title":"Recent Advances in Statistics","author":"Ferguson","year":"1983"},{"key":"ref147","first-page":"395","article-title":"Online learning of nonparametric mixture models via sequential variational approximation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lin"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1176347749"},{"key":"ref149","first-page":"1185","article-title":"The Indian buffet process: An introduction and review","volume":"12","author":"Griffiths","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref150","first-page":"977","article-title":"Modeling dyadic data with binary latent factors","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Meeds"},{"key":"ref151","first-page":"5250","article-title":"Learning where to learn: Gradient sparsity in meta and continual learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"von Oswald"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.2118\/18761-MS"},{"key":"ref153","first-page":"1180","article-title":"Unsupervised domain adaptation by backpropagation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ganin"},{"key":"ref154","article-title":"Hypernetworks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ha"},{"key":"ref155","first-page":"667","article-title":"Dynamic filter networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Jia"},{"key":"ref156","article-title":"Bayesian hypernetworks","author":"Krueger","year":"2017"},{"key":"ref157","article-title":"Learning implicitly recurrent CNNs through parameter sharing","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Savarese"},{"key":"ref158","first-page":"523","article-title":"Learning feed-forward one-shot learners","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Bertinetto"},{"key":"ref159","article-title":"Meta-learning via hypernetworks","volume-title":"Proc. 4th Workshop Meta-Learn. Neural Inf. Process. Syst.","author":"Zhao"},{"key":"ref160","first-page":"27075","article-title":"Hypertransformer: Model generation for supervised and semi-supervised few-shot learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhmoginov"},{"key":"ref161","article-title":"Wasserstein auto-encoders","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Tolstikhin"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.368"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00921"},{"key":"ref164","article-title":"Objects as points","author":"Zhou","year":"2019"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00972"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00755"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00459"},{"key":"ref168","first-page":"5276","article-title":"Incremental few-shot learning with attention attractor networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ren"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3185549"},{"key":"ref170","article-title":"Efficiently modeling long sequences with structured state spaces","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gu"},{"key":"ref171","first-page":"29348","article-title":"Mind the gap: Assessing temporal generalization in neural language models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lazaridou"},{"key":"ref172","article-title":"Towards continual knowledge learning of language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Jang"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.418"},{"key":"ref174","first-page":"13604","article-title":"StreamingQA: A benchmark for adaptation to new knowledge over time in question answering models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Livska"},{"key":"ref175","first-page":"5401","article-title":"Carpe diem: On the evaluation of world knowledge in lifelong language models","volume-title":"Proc. Conf. North Amer. Assoc. Comput. Linguistics: Hum. Lang. Technol.","author":"Kim"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00459"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.268"},{"key":"ref178","article-title":"A survey of imitation learning: Algorithms, recent developments, and challenges","author":"Zare","year":"2023"},{"key":"ref179","article-title":"Active learning literature survey","author":"Settles","year":"2009"},{"key":"ref180","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.582"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3367329"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10777928\/10684017.pdf?arnumber=10684017","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,5]],"date-time":"2024-12-05T06:00:29Z","timestamp":1733378429000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10684017\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":182,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3463709","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":[[2025,1]]}}}