{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T20:05:25Z","timestamp":1780949125812,"version":"3.54.1"},"reference-count":89,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"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":["62306326"],"award-info":[{"award-number":["62306326"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62472138"],"award-info":[{"award-number":["62472138"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004761","name":"Natural Science Foundation of Hainan Province","doi-asserted-by":"publisher","award":["2025JJ60461"],"award-info":[{"award-number":["2025JJ60461"]}],"id":[{"id":"10.13039\/501100004761","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Innovation Research Foundation of National University of Defense Technology","award":["ZK23-09"],"award-info":[{"award-number":["ZK23-09"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1109\/tpami.2026.3665061","type":"journal-article","created":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T21:06:50Z","timestamp":1771276010000},"page":"7590-7606","source":"Crossref","is-referenced-by-count":0,"title":["Tail Task Risk Minimization in Meta-Learning From Theoretical Advances to Practical Strategies"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1181-0212","authenticated-orcid":false,"given":"Yiqin","family":"Lv","sequence":"first","affiliation":[{"name":"College of Science, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4899-6113","authenticated-orcid":false,"given":"Dong","family":"Liang","sequence":"additional","affiliation":[{"name":"College of Science, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7825-9002","authenticated-orcid":false,"given":"Wumei","family":"Du","sequence":"additional","affiliation":[{"name":"College of Science, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1889-1409","authenticated-orcid":false,"given":"Zenglin","family":"Shi","sequence":"additional","affiliation":[{"name":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0391-8725","authenticated-orcid":false,"given":"Zheng","family":"Xie","sequence":"additional","affiliation":[{"name":"College of Science, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7758-725X","authenticated-orcid":false,"given":"Qi","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Science, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3094-7735","authenticated-orcid":false,"given":"Meng","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403207"},{"key":"ref2","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Brown","year":"2020"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2021.3098854"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06668-3"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3079209"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.xinn.2023.100516"},{"key":"ref7","first-page":"669","article-title":"Does GPT-3 generate empathetic dialogues? A novel in-context example selection method and automatic evaluation metric for empathetic dialogue generation","volume-title":"Proc. 29th Int. Conf. Comput. Linguistics","author":"Lee","year":"2022"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095697"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.nlpmc-1.9"},{"key":"ref10","first-page":"12897","article-title":"A simple yet effective strategy to robustify the meta learning paradigm","volume-title":"Proc. 37th Conf. Neural Inf. Process. Syst.","author":"Wang","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21314\/JOR.2000.038"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1002\/wics.194"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01199"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.195"},{"key":"ref15","article-title":"Diversity-driven data selection for language model tuning through sparse autoencoder","author":"Yang","year":"2025"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1137\/0114053"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2637"},{"key":"ref18","article-title":"Distributionally robust neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Sagawa","year":"2020"},{"key":"ref19","first-page":"18860","article-title":"Task-robust model-agnostic meta-learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Collins","year":"2020"},{"key":"ref20","article-title":"Neural processes","author":"Garnelo","year":"2018"},{"key":"ref21","first-page":"1704","article-title":"Conditional neural processes","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Garnelo","year":"2018"},{"key":"ref22","article-title":"Meta-learning probabilistic inference for prediction","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gordon","year":"2018"},{"key":"ref23","article-title":"Bridge the inference gaps of neural processes via expectation maximization","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Wang","year":"2023"},{"key":"ref24","first-page":"8284","article-title":"Meta-learning stationary stochastic process prediction with convolutional neural processes","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Foong","year":"2020"},{"key":"ref25","first-page":"10018","article-title":"Doubly stochastic variational inference for neural processes with hierarchical latent variables","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang","year":"2020"},{"key":"ref26","first-page":"3755","article-title":"Function contrastive learning of transferable meta-representations","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Gondal","year":"2021"},{"key":"ref27","first-page":"1","article-title":"Learning expressive meta-representations with mixture of expert neural processes","volume-title":"Proc. 36th Conf. Neural Inf. Process. Syst.","author":"Wang","year":"2022"},{"key":"ref28","first-page":"6606","article-title":"Bootstrapping neural processes","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Lee","year":"2020"},{"key":"ref29","first-page":"23055","article-title":"Model-based meta reinforcement learning using graph structured surrogate models and amortized policy search","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang","year":"2022"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3287"},{"key":"ref31","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Finn","year":"2017"},{"key":"ref32","article-title":"Meta-SGD: Learning to learn quickly for few-shot learning","author":"Li","year":"2017"},{"key":"ref33","first-page":"3314","article-title":"Meta-curvature","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Park","year":"2019"},{"key":"ref34","first-page":"9537","article-title":"Probabilistic model-agnostic meta-learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Finn","year":"2018"},{"key":"ref35","article-title":"Recasting gradient-based meta-learning as hierarchical Bayes","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Grant","year":"2018"},{"key":"ref36","first-page":"113","article-title":"Meta-learning with implicit gradients","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Rajeswaran","year":"2019"},{"key":"ref37","first-page":"10","article-title":"Sharp-MAML: Sharpness-aware model-agnostic meta learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Abbas","year":"2022"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.5555\/3294996.3295163"},{"key":"ref39","first-page":"232","article-title":"Infinite mixture prototypes for few-shot learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Allen","year":"2019"},{"key":"ref40","first-page":"670","article-title":"Few-shot generative modelling with generative matching networks","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Bartunov","year":"2018"},{"key":"ref41","article-title":"Matching networks for one shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Vinyals","year":"2016"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01091"},{"key":"ref43","first-page":"1478","article-title":"Hypernetworks in meta-reinforcement learning","volume-title":"Proc. Conf. Robot Learn.","author":"Beck","year":"2023"},{"key":"ref44","first-page":"1","article-title":"Meta-learning via hypernetworks","volume-title":"Proc. 4th Workshop Meta-Learn. NeurIPS","author":"Zhao","year":"2020"},{"key":"ref45","first-page":"1842","article-title":"Meta-learning with memory-augmented neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Santoro","year":"2016"},{"key":"ref46","article-title":"RL$^{2}$2: Fast reinforcement learning via slow reinforcement learning","author":"Duan","year":"2016"},{"key":"ref47","article-title":"On fast adversarial robustness adaptation in model-agnostic meta-learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang","year":"2020"},{"key":"ref48","first-page":"17886","article-title":"Adversarially robust few-shot learning: A meta-learning approach","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Goldblum","year":"2020"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3690624.3709337"},{"key":"ref50","article-title":"Diverse client selection for federated learning via submodular maximization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Balakrishnan","year":"2022"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.32388\/fqn5fi"},{"key":"ref52","first-page":"543","article-title":"How important is the train-validation split in meta-learning?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bai","year":"2021"},{"key":"ref53","first-page":"1566","article-title":"Learning-to-learn stochastic gradient descent with biased regularization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Denevi","year":"2019"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.112580"},{"key":"ref55","article-title":"Robust optimization for non-convex objectives","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Chen","year":"2017"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.3003851"},{"key":"ref57","first-page":"1","article-title":"Adversarial distributional training for robust deep learning","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Dong","year":"2020"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108889"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.3934\/dcdsb.2017007"},{"key":"ref60","first-page":"3133","article-title":"Implicit learning dynamics in Stackelberg games: Equilibria characterization, convergence analysis, and empirical study","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fiez","year":"2020"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0847"},{"key":"ref62","article-title":"Bilevel optimization for machine learning: Algorithm design and convergence analysis","author":"Ji","year":"2021"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-3264-1"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.1120.1641"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1038\/sj.jors.2600425"},{"key":"ref66","first-page":"6083","article-title":"On gradient descent ascent for nonconvex-concave minimax problems","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lin","year":"2020"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/BF00121269"},{"key":"ref68","first-page":"1540","article-title":"Optimizing millions of hyperparameters by implicit differentiation","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Lorraine","year":"2020"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3132674"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/3086464"},{"key":"ref71","volume-title":"Mathematical Analysis","author":"Apostol","year":"1974"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i09.7123"},{"key":"ref73","article-title":"Carbon emissions and large neural network training","author":"Patterson","year":"2021"},{"key":"ref74","article-title":"Scaling laws for transfer","author":"Hernandez","year":"2021"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1016\/j.metrad.2023.100017"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1016\/j.lindif.2023.102274"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.295"},{"key":"ref78","article-title":"LLMCarbon: Modeling the end-to-end carbon footprint of large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Faiz","year":"2024"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2176"},{"issue":"2","key":"ref80","first-page":"65","article-title":"Empirical choice of histograms and kernel density estimators","volume":"9","author":"Rudemo","year":"1982","journal-title":"Scand. J. Statist."},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-43465-6_1"},{"key":"ref82","article-title":"Optimization as a model for few-shot learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Larochelle","year":"2017"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref84","first-page":"7693","article-title":"Fast context adaptation via meta-learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zintgraf","year":"2019"},{"key":"ref85","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"ref87","article-title":"Meta-learning for semi-supervised few-shot classification","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ren","year":"2018"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"ref89","article-title":"Learning robust global representations by penalizing local predictive power","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Wang","year":"2019"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11552636\/11397197.pdf?arnumber=11397197","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T19:52:04Z","timestamp":1780948324000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11397197\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":89,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3665061","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":[[2026,7]]}}}