{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T16:27:19Z","timestamp":1781972839678,"version":"3.54.5"},"reference-count":300,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tpami.2021.3079209","type":"journal-article","created":{"date-parts":[[2021,5,11]],"date-time":"2021-05-11T20:23:31Z","timestamp":1620764611000},"page":"1-1","source":"Crossref","is-referenced-by-count":1013,"title":["Meta-Learning in Neural Networks: A Survey"],"prefix":"10.1109","author":[{"given":"Timothy M","family":"Hospedales","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Antreas","family":"Antoniou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paul","family":"Micaelli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amos J.","family":"Storkey","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/vl\/N19-142"},{"key":"ref4","article-title":"Deep learning: A critical pppraisal,","author":"Marcus","year":"2018"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1021\/acscentsci.6b00367"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00447"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-5529-2_1"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1037\/h0062474"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1111\/j.2044-8279.1985.tb02625.x"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/BF02382299"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2347736.2347755"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1023\/b:visi.0000029664.99615.94"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref14","article-title":"Optimization as a model for few-shot learning,","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ravi"},{"key":"ref15","first-page":"3988","article-title":"Learning to learn by gradient descent by gradient descent,","volume-title":"Proc. 30th Int. Conf. Neural Inf. Process. Syst.","author":"Andrychowicz"},{"key":"ref16","article-title":"Meta-learning update rules for unsupervised representation learning,","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Metz"},{"key":"ref17","article-title":"Evolutionary principles in self-referential learning. On learning now to learn: The meta-meta-meta...-hook,","author":"Schmidhuber","year":"1987"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1023\/A:1007383707642","article-title":"Shifting inductive bias with success-story algorithm, adaptive Levin search, and incremental self-improvement,","volume":"28","author":"Schmidhuber","year":"1997","journal-title":"Mach. Learn."},{"key":"ref19","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks,","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Finn"},{"key":"ref20","first-page":"1568","article-title":"Bilevel programming for hyperparameter optimization and meta-learning,","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Franceschi"},{"key":"ref21","article-title":"DARTS: Differentiable architecture search,","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu"},{"key":"ref22","article-title":"Online meta-critic learning for off-policy actor-critic methods,","volume-title":"Proc. 34th Conf. Neural Inf. Process. Syst.","author":"Zhou"},{"key":"ref23","article-title":"Prototypical Networks for few shot learning,","volume-title":"Proc. 31st Conf. Neural Inf. Process. Syst.","author":"Snell"},{"key":"ref24","article-title":"RL$^2$2: Fast reinforcement learning via slow reinforcement learning,","author":"Duan","year":"2016"},{"key":"ref25","article-title":"Evolved policy gradients,","volume-title":"Proc. 32nd Conf. Neural Inf. Process. Syst.","author":"Houthooft"},{"key":"ref26","article-title":"Meta-learning curiosity algorithms,","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Alet"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014780"},{"key":"ref28","article-title":"Neural architecture search with reinforcement learning,","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zoph"},{"key":"ref29","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1023\/A:1019956318069","article-title":"A perspective view and survey of meta-learning,","volume":"18","author":"Vilalta","year":"2002","journal-title":"Artif. Intell. Rev."},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-5529-2_8"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-5529-2_4"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1996.8.7.1341"},{"key":"ref33","article-title":"Meta-learning: A survey,","author":"Vanschoren","year":"2018"},{"key":"ref34","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-05318-5","volume-title":"Automatic Machine Learning: Methods, Systems, Challenges","author":"Hutter","year":"2019"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-013-9406-y"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3386252"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-05318-5_3"},{"key":"ref39","article-title":"A simple neural attentive meta-learner,","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Mishra"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.2307\/2550609"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2017.2712906"},{"key":"ref42","first-page":"3915","article-title":"Feature-critic networks for heterogeneous domain generalization,","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref43","article-title":"Learning to learn around a common mean,","volume-title":"Proc. 32nd Conf. Neural Inf. Process. Syst.","author":"Denevi"},{"key":"ref44","first-page":"3394","article-title":"Deep sets,","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Zaheer"},{"key":"ref45","first-page":"3915","article-title":"Meta-learning probabilistic inference for prediction,","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gordon"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.1991.155621"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/BF02279935"},{"key":"ref48","article-title":"Simple principles of meta-learning,","author":"Schmidhuber","year":"1996"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICNN.1993.298591"},{"key":"ref50","first-page":"222","article-title":"A possibility for implementing curiosity and boredom in model-building neural controllers,","volume-title":"Proc. Animals Animats, 1st Int. Conf. Simul. Adaptive Behav.","author":"Meyer"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-44668-0_13"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2001.938471"},{"key":"ref53","first-page":"159","article-title":"Reinforcement driven information acquisition in non-deterministic environments,","volume-title":"Proc. Int. Conf. Artif. Neural Netw.","author":"Storck"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/3119.003.0034"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(02)00228-9"},{"key":"ref56","first-page":"584","article-title":"Direct transfer of learned information among neural networks,","volume-title":"Proc. Assoc. Adv. Artif. Intell.","author":"Pratt"},{"key":"ref57","first-page":"3320","article-title":"How transferable are features in deep neural networks?,","volume-title":"Proc. 27th Int. Conf. Neural Inf. Process. Syst.","author":"Yosinski"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-58347-1"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_23"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.01.012"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.2200\/s00832ed1v01y201802aim037"},{"key":"ref62","article-title":"Continuous adaptation via meta-learning in nonstationary and competitive environments,","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Al-Shedivat"},{"key":"ref63","first-page":"4354","article-title":"Been there, done that: Meta-learning with episodic recall,","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Ritter"},{"key":"ref64","article-title":"Learning to adapt in dynamic, real-world environments through meta-reinforcement learning,","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Clavera"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007379606734"},{"key":"ref66","article-title":"Deep multi-task representation learning: A tensor factorisation approach,","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yang"},{"key":"ref67","first-page":"1165","article-title":"Forward and reverse gradient-based hyperparameter optimization,","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Franceschi"},{"key":"ref68","article-title":"Adaptive auxiliary task weighting for reinforcement learning,","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lin"},{"key":"ref69","article-title":"Non-greedy gradient-based hyperparameter optimization over long horizons,","author":"Micaelli","year":"2020"},{"key":"ref70","first-page":"281","article-title":"Random search for hyper-parameter optimization,","volume":"13","author":"Bergstra","year":"2012","journal-title":"J. Mach. Learn. Res."},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2015.2494218"},{"key":"ref72","first-page":"993","article-title":"Latent Dirchlet allocation,","volume":"3","author":"Blei","year":"2003","journal-title":"J. Mach. Learn. Res."},{"key":"ref73","article-title":"Towards a neural statistician,","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Edwards"},{"key":"ref74","article-title":"Recasting gradient-based meta-learning as hierarchical Bayes,","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Grant"},{"key":"ref75","article-title":"Automated relational meta-learning,","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yao"},{"key":"ref76","first-page":"2927","article-title":"Gradient-based meta-learning with learned layerwise metric and subspace,","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Yoonho Lee"},{"key":"ref77","article-title":"Meta-SGD: Learning to learn quickly for few shot learning,","author":"Li","year":"2017"},{"key":"ref78","article-title":"How to train your MAML,","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Antoniou"},{"key":"ref79","article-title":"Learning to optimize,","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li"},{"key":"ref80","article-title":"Generalized inner loop meta-learning,","author":"Grefenstette","year":"2019"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00755"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00459"},{"key":"ref83","article-title":"Neural turing machines,","author":"Graves","year":"2014"},{"key":"ref84","article-title":"Meta learning with memory-augmented neural networks,","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Santoro"},{"key":"ref85","first-page":"2554","article-title":"Meta networks,","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Munkhdalai"},{"key":"ref86","first-page":"1","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":"ref87","article-title":"Siamese neural networks for one-shot image recognition,","volume-title":"Proc. 32nd Int. Conf. Mach. Learn.","author":"Kosh"},{"key":"ref88","article-title":"Matching networks for one shot learning,","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Vinyals"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00131"},{"key":"ref90","first-page":"1","article-title":"Few-shot learning with graph neural networks,","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Garcia"},{"key":"ref91","first-page":"459","article-title":"Neural optimizer search with reinforcement learning,","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bello"},{"key":"ref92","first-page":"3751","article-title":"Learned optimizers that scale and generalize,","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wichrowska"},{"key":"ref93","first-page":"1","article-title":"MetaReg: Towards domain generalization using meta-regularization,","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Balaji"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00519"},{"key":"ref95","article-title":"Adversarially robust few-shot learning: A meta-learning approach,","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Goldblum"},{"key":"ref96","first-page":"9537","article-title":"Probabilistic model-agnostic meta-learning,","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Finn"},{"key":"ref97","article-title":"Online meta-learning,","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Finn"},{"key":"ref98","article-title":"Meta-learning with latent embedding optimization,","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Rusu"},{"key":"ref99","article-title":"Learning to learn by self-critique,","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Antoniou"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00049"},{"key":"ref101","article-title":"Multimodal model-agnostic meta-learning via task-aware modulation,","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Vuorio"},{"key":"ref102","first-page":"7045","article-title":"Hierarchically structured meta-learning,","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Yao"},{"key":"ref103","first-page":"1","article-title":"Adam: A method for stochastic optimization,","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma"},{"key":"ref104","article-title":"Meta-curvature,","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Park"},{"key":"ref105","article-title":"Meta-learning with warped gradient descent,","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Flennerhag"},{"key":"ref106","first-page":"748","article-title":"Learning to learn without gradient descent by gradient descent,","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref107","article-title":"Empirical Bayes for learning to learn,","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Heskes"},{"key":"ref108","article-title":"Fast and flexible multi-task classification using conditional neural adaptive processes,","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Requeima"},{"key":"ref109","article-title":"Meta-dataset: A dataset of datasets for learning to learn from few examples,","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Triantafillou"},{"key":"ref110","article-title":"HyperNetworks,","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ha"},{"key":"ref111","first-page":"5331","article-title":"Efficient off-policy meta-reinforcement learning via probabilistic context variables,","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Rakelly"},{"key":"ref112","article-title":"One-shot imitation learning,","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Duan"},{"key":"ref113","article-title":"Learning to reinforcement learn,","author":"Wang","year":"2016"},{"key":"ref114","article-title":"A closer look at few-shot classification,","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen"},{"key":"ref115","article-title":"TADAM: Task dependent adaptive metric for improved few-shot learning,","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Oreshkin"},{"key":"ref116","first-page":"1","article-title":"Cross-domain few-shot classification via learned feature-wise transformation,","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Tseng"},{"key":"ref117","article-title":"Learning to learn: Meta-critic networks for sample efficient learning,","author":"Sung","year":"2017"},{"key":"ref118","first-page":"1","article-title":"Online-within-online meta-learning,","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Denevi"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/CEC48606.2020.9185777"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412010"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00660"},{"key":"ref122","first-page":"1","article-title":"Semi-supervised few-shot learning with MAML,","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Rinu Boney"},{"key":"ref123","first-page":"2891","article-title":"Addressing the loss-metric mismatch with adaptive loss alignment,","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Huang"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.226"},{"key":"ref125","article-title":"Reinforcement learning with unsupervised auxiliary tasks,","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Jaderberg"},{"key":"ref126","first-page":"1677","article-title":"Self-supervised generalisation with meta auxiliary learning,","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-018-0006-z"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-04277-5_76"},{"key":"ref129","first-page":"1","article-title":"SNAS: Stochastic neural architecture search,","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xie"},{"key":"ref130","article-title":"Understanding and robustifying differentiable architecture search,","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zela"},{"key":"ref131","first-page":"1","article-title":"Towards fast adaptation of neural architectures with meta learning,","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lian"},{"key":"ref132","article-title":"Meta architecture search,","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Shaw"},{"key":"ref133","article-title":"Cross attention network for few-shot classification,","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Hou"},{"key":"ref134","first-page":"1","article-title":"Incremental few-shot learning with attention attractor networks,","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Ren"},{"key":"ref135","first-page":"1","article-title":"Few-shot text classification with distributional signatures,","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bao"},{"key":"ref136","first-page":"856","article-title":"Modular meta-learning,","volume-title":"Proc. 2nd Conf. Robot Learn.","author":"Alet"},{"key":"ref137","first-page":"1","article-title":"Neural relational inference with fast modular meta-learning,","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Alet"},{"key":"ref138","article-title":"PathNet: Evolution channels gradient descent in super neural networks,","author":"Fernando","year":"2017"},{"key":"ref139","first-page":"1","article-title":"Compositional generalization through meta sequence-to-sequence learning,","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Lake"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00020"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58542-6_35"},{"key":"ref142","first-page":"33","article-title":"Model vulnerability to distributional shifts over image transformation sets,","volume-title":"Proc. Int. Conf. Comput. Vis.","author":"Volpi"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3049011"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015741"},{"key":"ref145","first-page":"1","article-title":"Online batch selection for faster training of neural networks,","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.4324\/9780203416013_chapter_1"},{"key":"ref147","first-page":"1917","article-title":"Meta-weight-net: Learning an explicit mapping for sample weighting,","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Shu"},{"key":"ref148","first-page":"4334","article-title":"Learning to reweight examples for robust deep learning,","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Ren"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1016\/0010-0277(93)90058-4"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref151","first-page":"2304","article-title":"MentorNet: Learning data-driven curriculum for very deep neural networks on corrupted labels,","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Jiang"},{"key":"ref152","article-title":"Dataset distillation,","author":"Wang","year":"2018"},{"key":"ref153","article-title":"Dataset condensation with gradient matching,","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhao"},{"key":"ref154","first-page":"1540","article-title":"Optimizing millions of hyperparameters by implicit differentiation,","volume-title":"Proc. 23rd Int. Conf. Artif. Intell. Stat.","author":"Lorraine"},{"key":"ref155","article-title":"Flexible dataset distillation: Learn labels instead of images,","author":"Bohdal","year":"2020"},{"key":"ref156","article-title":"Learning to impute: A general framework for semi-supervised learning,","author":"Li","year":"2019"},{"key":"ref157","article-title":"Learning to self-train for semi-supervised few-shot classification,","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Sun"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"},{"key":"ref159","first-page":"1","article-title":"Learning to simulate,","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ruiz"},{"key":"ref160","article-title":"How To pick the domain randomization parameters for sim-to-real transfer of reinforcement learning policies?,","author":"Vuong","year":"2019"},{"key":"ref161","article-title":"Searching for activation functions,","author":"Le","year":"2017"},{"key":"ref162","article-title":"Learning to balance: Bayesian meta-learning for imbalanced and out-of-distribution tasks,","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lee"},{"key":"ref163","first-page":"1","article-title":"Meta-learning with implicit gradients,","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Rajeswaran"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01091"},{"key":"ref165","first-page":"1","article-title":"Meta-learning with differentiable closed-form solvers,","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bertinetto"},{"key":"ref166","article-title":"Meta-Q-learning,","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Fakoor"},{"key":"ref167","first-page":"4061","article-title":"Taming MAML: Efficient unbiased meta-reinforcement learning,","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Liu"},{"key":"ref168","article-title":"ProMP: Proximal meta-policy search,","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Rothfuss"},{"key":"ref169","article-title":"ES-MAML: Simple Hessian-free meta learning,","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1145\/3205651.3205763"},{"key":"ref171","article-title":"Meta continual learning,","author":"Vuorio","year":"2018"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/581"},{"key":"ref173","first-page":"1","article-title":"Meta-gradient reinforcement learning,","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Xu"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1126\/science.aau6249"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01386"},{"key":"ref176","first-page":"1704","article-title":"Conditional neural processes,","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Garnelo"},{"key":"ref177","first-page":"7455","article-title":"Neural clustering processes,","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Pakman"},{"key":"ref178","first-page":"3744","article-title":"Set transformer: A framework for attention-based permutation-invariant neural networks,","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Lee"},{"key":"ref179","article-title":"Deep amortized clustering,","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lee"},{"key":"ref180","article-title":"Discovery of useful questions as auxiliary tasks,","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Veeriah"},{"key":"ref181","first-page":"1","article-title":"On learning intrinsic rewards for policy gradient methods,","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Zheng"},{"key":"ref182","first-page":"5463","article-title":"Learning to explore with meta-policy gradient,","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xu"},{"key":"ref183","article-title":"Some considerations on learning to explore via meta-reinforcement learning,","volume-title":"Proc. 36th Int. Conf. Neural Inf. Process. Syst.","author":"Stadie"},{"key":"ref184","first-page":"1","article-title":"A meta-MDP approach to exploration for lifelong reinforcement learning,","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Garcia"},{"key":"ref185","first-page":"5307","article-title":"Meta-reinforcement learning of structured exploration strategies,","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Gupta"},{"key":"ref186","first-page":"1","article-title":"Meta dropout: Learning to perturb latent features for generalization,","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lee"},{"key":"ref187","first-page":"301","article-title":"Learning algorithms for active learning,","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bachman"},{"key":"ref188","first-page":"1","article-title":"Learning active learning from data,","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Konyushkova"},{"key":"ref189","article-title":"Meta-learning transferable active learning policies by deep reinforcement learning,","author":"Pang","year":"2018"},{"key":"ref190","first-page":"2113","article-title":"Gradient-based hyperparameter optimization through reversible learning,","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Maclaurin"},{"key":"ref191","first-page":"1","article-title":"Fixing implicit derivatives: Trust-region based learning of continuous energy functions,","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Russell"},{"key":"ref192","article-title":"On first-order meta-learning algorithms,","author":"Nichol","year":"2018"},{"key":"ref193","article-title":"Evolution strategies as a scalable alternative to reinforcement learning,","author":"Salimans","year":"2017"},{"key":"ref194","doi-asserted-by":"publisher","DOI":"10.2478\/pjbr-2013-0003"},{"key":"ref195","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2018.07.013"},{"key":"ref196","first-page":"1","article-title":"Learning to optimize in swarms,","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Cao"},{"key":"ref197","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460625"},{"key":"ref198","first-page":"1","article-title":"Online learning rate adaptation with hypergradient descent,","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Baydin"},{"key":"ref199","first-page":"1","article-title":"MetaQuant: Learning to quantize by learning to penetrate non-differentiable quantization,","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref200","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.97"},{"key":"ref201","article-title":"Meta-learning without memorization,","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yin"},{"key":"ref202","first-page":"7115","article-title":"TapNet: Neural network augmented with task-adaptive projection for few-shot learning,","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yoon"},{"key":"ref203","first-page":"5271","article-title":"Meta-learning neural bloom filters,","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rae"},{"key":"ref204","first-page":"1","article-title":"Rapid learning or feature reuse? Towards understanding the effectiveness of MAML,","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Raghu"},{"key":"ref205","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00851"},{"key":"ref206","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_27"},{"key":"ref207","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.167"},{"key":"ref208","first-page":"1","article-title":"Few-shot semantic segmentation with prototype learning,","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Dong"},{"key":"ref209","article-title":"Few-shot segmentation propagation with guided networks,","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rakelly"},{"key":"ref210","first-page":"1","article-title":"TARN: Temporal attentive relation network for few-shot and zero-shot action recognition,","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Bishay"},{"key":"ref211","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3058606"},{"key":"ref212","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_27"},{"key":"ref213","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar6170"},{"key":"ref214","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00955"},{"key":"ref215","article-title":"Few-shot video-to-video synthesis,","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref216","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00841"},{"key":"ref217","article-title":"Few-shot autoregressive density estimation: towards learning to learn distributions,","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Reed"},{"key":"ref218","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref219","first-page":"1","article-title":"Meta-learning for semi-supervised few-shot classification,","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Ren"},{"key":"ref220","article-title":"Defining benchmarks for continual few-shot learning,","author":"Antoniou","year":"2020"},{"key":"ref221","article-title":"Learning multiple visual domains with residual adapters,","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Rebuffi"},{"key":"ref222","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58583-9_8"},{"key":"ref223","first-page":"52","article-title":"Does object recognition work for everyone?,","volume-title":"Proc. Conf. Comput. Vis. Pattern Recognit.","author":"De Vries"},{"key":"ref224","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022672621406"},{"key":"ref225","article-title":"Provably convergent policy gradient methods for model-agnostic meta-reinforcement learning,","author":"Fallah","year":"2020"},{"key":"ref226","article-title":"Proximal policy optimization algorithms,","author":"Schulman","year":"2017"},{"key":"ref227","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.01.011"},{"key":"ref228","article-title":"Whats interesting?,","author":"Schmidhuber","year":"1997"},{"key":"ref229","article-title":"Improving generalization in meta reinforcement learning using learned objectives,","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kirsch"},{"key":"ref230","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor,","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref231","first-page":"1","article-title":"A review of robot learning for manipulation: Challenges, representations, and algorithms,","volume":"22","author":"Kroemer","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref232","article-title":"Unsupervised curricula for visual meta-reinforcement learning,","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Jabri"},{"key":"ref233","first-page":"323","article-title":"NoRML: No-reward meta learning,","volume-title":"Proc. Int. Conf. Autonom. Agents Multi-Agent Syst.","author":"Yang"},{"key":"ref234","first-page":"1","article-title":"SMILe: Scalable meta inverse reinforcement learning through context-conditional policies,","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Ghasemipour"},{"key":"ref235","doi-asserted-by":"publisher","DOI":"10.1613\/jair.5699"},{"key":"ref236","article-title":"Gotta learn fast: A new benchmark for generalization in RL,","author":"Nichol","year":"2018"},{"key":"ref237","first-page":"1282","article-title":"Quantifying generalization in reinforcement learning,","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Cobbe"},{"key":"ref238","article-title":"OpenAI gym,","author":"Brockman","year":"2016"},{"key":"ref239","article-title":"Assessing generalization in deep reinforcement learning,","author":"Packer","year":"2018"},{"key":"ref240","article-title":"Investigating generalisation in continuous deep reinforcement learning,","author":"Zhao","year":"2019"},{"key":"ref241","article-title":"Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning,","author":"Yu","year":"2019"},{"key":"ref242","article-title":"PHYRE: A new benchmark for physical reasoning,","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Bakhtin"},{"key":"ref243","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00907"},{"key":"ref244","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01238"},{"key":"ref245","first-page":"7105","article-title":"NAS-bench-101: Towards reproducible neural architecture search,","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ying"},{"key":"ref246","article-title":"Adaptive deep kernel learning,","author":"Tossou","year":"2019"},{"key":"ref247","article-title":"Deep kernel transfer in Gaussian processes for few-shot learning,","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Patacchiola"},{"key":"ref248","article-title":"Bayesian model-agnostic meta-learning,","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Kim"},{"key":"ref249","first-page":"1","article-title":"Amortized Bayesian meta-learning,","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ravi"},{"key":"ref250","first-page":"1","article-title":"Bayesian meta sampling for fast uncertainty adaptation,","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang"},{"key":"ref251","first-page":"1","article-title":"Unsupervised learning via meta-learning,","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hsu"},{"key":"ref252","first-page":"10132","article-title":"Unsupervised meta-learning for few-shot image classification,","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Khodadadeh"},{"key":"ref253","article-title":"Assume, augment and learn: Unsupervised few-shot meta-learning via random labels and data augmentation,","author":"Antoniou","year":"2019"},{"key":"ref254","article-title":"Meta-learning to cluster,","author":"Jiang","year":"2019"},{"key":"ref255","article-title":"Supervising unsupervised learning,","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Garg"},{"key":"ref256","article-title":"Meta-learned confidence for few-shot learning,","author":"Kye","year":"2020"},{"key":"ref257","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01139"},{"key":"ref258","first-page":"1","article-title":"Meta-learning representations for continual learning,","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Javed"},{"key":"ref259","first-page":"1","article-title":"Editable neural networks,","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Sinitsin"},{"key":"ref260","article-title":"Domain generalization via invariant feature representation,","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Muandet"},{"key":"ref261","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11596"},{"key":"ref262","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.591"},{"key":"ref263","first-page":"1","article-title":"Neural program meta-induction,","volume-title":"Proc. 31st Conf. Neural Inf. Process. Syst.","author":"Devlin"},{"key":"ref264","first-page":"1","article-title":"Learning a meta-solver for syntax-guided program synthesis,","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Si"},{"key":"ref265","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2115"},{"key":"ref266","article-title":"Meta learning with relational information for short sequences,","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Xie"},{"key":"ref267","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1398"},{"key":"ref268","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1542"},{"key":"ref269","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053112"},{"key":"ref270","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-45"},{"key":"ref271","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1244"},{"key":"ref272","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00143"},{"key":"ref273","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00465"},{"key":"ref274","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2019.4337"},{"key":"ref275","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00928-1_62"},{"key":"ref276","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32251-9_57"},{"key":"ref277","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-33391-1_24"},{"key":"ref278","first-page":"3559","article-title":"Differentiable plasticity: Training plastic neural networks with backpropagation,","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Miconi"},{"key":"ref279","article-title":"Backpropamine: Training self-modifying neural networks with differentiable neuromodulated plasticity,","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Miconi"},{"key":"ref280","article-title":"Compressing neural networks using the variational information bottleneck,","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Dai"},{"key":"ref281","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00339"},{"key":"ref282","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2017.2758370"},{"key":"ref283","doi-asserted-by":"publisher","DOI":"10.1109\/SPAWC.2019.8815537"},{"key":"ref284","doi-asserted-by":"publisher","DOI":"10.2200\/S00429ED1V01Y201207AIM018"},{"key":"ref285","article-title":"Explaining and harnessing adversarial examples,","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Goodfellow"},{"key":"ref286","article-title":"Adversarial meta-learning,","author":"Yin","year":"2018"},{"key":"ref287","first-page":"1","article-title":"A meta-learning perspective on cold-start recommendations for items,","volume-title":"Proc. 31st Conf. Neural Inf. Process. Syst.","author":"Vartak"},{"key":"ref288","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2019.8852100"},{"key":"ref289","article-title":"Gradient surgery for multi-task learning,","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Yu"},{"key":"ref290","first-page":"521","article-title":"Learning with whom to share in multi-task feature learning,","volume-title":"Proc. 25th Int. Conf. Mach. Learn.","author":"Kang"},{"key":"ref291","first-page":"1","article-title":"A unified perspective on multi-domain and multi-task learning,","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yang"},{"key":"ref292","first-page":"232","article-title":"Infinite mixture prototypes for few-shot learning,","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Allen"},{"key":"ref293","first-page":"737","article-title":"Hyperparameter optimization with approximate gradient,","volume-title":"Proc. 33rd Int. Conf. Mach. Learn.","author":"Pedregosa"},{"key":"ref294","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.2.270"},{"key":"ref295","article-title":"Tasks, stability, architecture, and compute: Training more effective learned optimizers, and using them to train themselves,","author":"Metz","year":"2020"},{"key":"ref296","article-title":"Truncated back-propagation for bilevel optimization,","volume-title":"Proc. 22nd Int. Conf. Artif. Intell. Stat.","author":"Shaban"},{"key":"ref297","first-page":"1469","article-title":"DrMAD: Distilling reverse-mode automatic differentiation for optimizing hyperparameters of deep neural networks,","volume-title":"Proc. 25th Int. Joint Conf. Artif. Intell.","author":"Fu"},{"key":"ref298","first-page":"1","article-title":"Transferring knowledge across learning processes,","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Flennerhag"},{"key":"ref299","first-page":"1","article-title":"Understanding short-horizon bias in stochastic meta-optimization,","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wu"},{"key":"ref300","article-title":"Understanding and correcting pathologies in the training of learned optimizers,","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Metz"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/4359286\/09428530.pdf?arnumber=9428530","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,9]],"date-time":"2024-01-09T23:11:32Z","timestamp":1704841892000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9428530\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":300,"URL":"https:\/\/doi.org\/10.1109\/tpami.2021.3079209","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":[[2021]]}}}