{"id":13444456,"url":"https://github.com/dragen1860/awesome-meta-learning","last_synced_at":"2026-02-02T23:16:05.900Z","repository":{"id":48139826,"uuid":"153083544","full_name":"dragen1860/awesome-meta-learning","owner":"dragen1860","description":"A curated list of Meta-Learning resources/papers.","archived":false,"fork":false,"pushed_at":"2020-12-21T08:23:01.000Z","size":524,"stargazers_count":554,"open_issues_count":2,"forks_count":98,"subscribers_count":24,"default_branch":"master","last_synced_at":"2025-11-01T02:02:59.933Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/dragen1860.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2018-10-15T09:04:19.000Z","updated_at":"2025-10-09T07:45:44.000Z","dependencies_parsed_at":"2022-09-19T06:41:02.639Z","dependency_job_id":null,"html_url":"https://github.com/dragen1860/awesome-meta-learning","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/dragen1860/awesome-meta-learning","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dragen1860%2Fawesome-meta-learning","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dragen1860%2Fawesome-meta-learning/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dragen1860%2Fawesome-meta-learning/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dragen1860%2Fawesome-meta-learning/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/dragen1860","download_url":"https://codeload.github.com/dragen1860/awesome-meta-learning/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dragen1860%2Fawesome-meta-learning/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29022777,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-02T22:20:39.141Z","status":"ssl_error","status_checked_at":"2026-02-02T22:20:37.621Z","response_time":58,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-07-31T04:00:23.613Z","updated_at":"2026-02-02T23:16:05.872Z","avatar_url":"https://github.com/dragen1860.png","language":null,"funding_links":[],"categories":["Uncategorized","Others","Table of Contents","Meta Learning"],"sub_categories":["Uncategorized"],"readme":"# awesome-meta-learning [![Awesome](https://awesome.re/badge.svg)](https://awesome.re)\n\nA curated list of Meta-Learning resources. Inspired by [awesome-deep-vision](https://github.com/kjw0612/awesome-deep-vision), [awesome-adversarial-machine-learning](https://github.com/yenchenlin/awesome-adversarial-machine-learning), [awesome-deep-learning-papers](https://github.com/terryum/awesome-deep-learning-papers), and [awesome-architecture-search](https://github.com/markdtw/awesome-architecture-search).\n\nPlease feel free to [pull requests](https://github.com/dragen1860/awesome-meta-learning/pulls) or [open an issue](https://github.com/dragen1860/awesome-meta-learning/issues) to add papers.\n \n\n![learning2learn](learning2learn.jpg)\n\n# Papers and Code\n\n* [Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples](https://arxiv.org/pdf/1903.03096v1.pdf). Eleni Triantafillou, Tyler Zhu, Vincent Dumoulin, Pascal Lamblin, Kelvin Xu, Ross Goroshin, Carles Gelada, Kevin Swersky, Pierre-Antoine Manzagol, Hugo Larochelle.\n\n* [Gradient-Based Meta-Learning with Learned Layerwise Metric and Subspace](https://arxiv.org/abs/1801.05558). Yoonho Lee, Seungjin Choi.\n[![Code](github.jpg)](https://github.com/yoonholee/MT-net)\n\n* [FIGR: Few-shot Image Generation with Reptile](https://arxiv.org/abs/1901.02199). Louis Clouâtre, Marc Demers.\n\n* [Online gradient-based mixtures for transfer modulation in meta-learning](https://arxiv.org/abs/1812.06080). Ghassen Jerfel, Erin Grant, Thomas L. Griffiths, Katherine Heller.\n\n* [Auto-Meta: Automated Gradient Based Meta Learner Search](https://arxiv.org/pdf/1806.06927.pdf). Jaehong Kim, Youngduck Choi, Moonsu Cha, Jung Kwon Lee, Sangyeul Lee, Sungwan Kim, Yongseok Choi, Jiwon Kim.\n\n* [MetaGAN: An Adversarial Approach to Few-Shot Learning](http://papers.nips.cc/paper/7504-metagan-an-adversarial-approach-to-few-shot-learning). ZHANG, Ruixiang and Che, Tong and Ghahramani, Zoubin and Bengio, Yoshua and Song, Yangqiu.\n\n* [Learned Optimizers that Scale and Generalize](https://arxiv.org/abs/1703.04813). Olga Wichrowska, Niru Maheswaranathan, Matthew W. Hoffman, Sergio Gomez Colmenarejo, Misha Denil, Nando de Freitas, Jascha Sohl-Dickstein.\n\n* [Guiding Policies with Language via Meta-Learning](https://arxiv.org/abs/1811.07882). John D. Co-Reyes, Abhishek Gupta, Suvansh Sanjeev, Nick Altieri, John DeNero, Pieter Abbeel, Sergey Levine.\n\n* [Deep Comparison: Relation Columns for Few-Shot Learning](https://128.84.21.199/abs/1811.07100?context=cs). Xueting Zhang, Flood Sung, Yuting Qiang, Yongxin Yang, Timothy M. Hospedales.\n\n* [Towards learning-to-learn](https://arxiv.org/abs/1811.00231). Benjamin James Lansdell, Konrad Paul Kording.\n\n* [Learning to Learn with Gradients](https://www2.eecs.berkeley.edu/Pubs/TechRpts/2018/EECS-2018-105.html). Finn, Chelsea. \n* [How to train your MAML](https://arxiv.org/abs/1810.09502). Antreas Antoniou, Harrison Edwards, Amos Storkey.\n[![Code](github.jpg)](https://github.com/AntreasAntoniou/HowToTrainYourMAMLPytorch)\n* [Learned optimizers that outperform SGD on wall-clock and validation loss](https://arxiv.org/abs/1810.10180). Luke Metz, Niru Maheswaranathan, Jeremy Nixon, C. Daniel Freeman, Jascha Sohl-Dickstein\n* [Gradient Agreement as an Optimization Objective for Meta-Learning](https://arxiv.org/pdf/1810.08178.pdf). Amir Erfan Eshratifar, David Eigen, Massoud Pedram. \n* [Few-Shot Image Recognition by Predicting Parameters from Activations](https://arxiv.org/abs/1706.03466). Siyuan Qiao, Chenxi Liu, Wei Shen, Alan Yuille. CVPR 2018.\n[![Code](github.jpg)](https://github.com/joe-siyuan-qiao/FewShot-CVPR)\n* [META-LEARNING WITH LATENT EMBEDDING OPTIMIZATION](https://arxiv.org/pdf/1807.05960.pdf). Andrei A. Rusu, Dushyant Rao, Jakub Sygnowski, Oriol Vinyals, Razvan Pascanu, Simon Osindero \u0026 Raia Hadsell\n* [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://arxiv.org/abs/1703.03400), Chelsea Finn, Pieter Abbeel, Sergey Levine. ICML 2017.\n[![Code](github.jpg)](https://github.com/cbfinn/maml) [![Code](github.jpg)](https://github.com/cbfinn/maml_rl) [![Code](github.jpg)](https://github.com/dragen1860/MAML-Pytorch) [![Code](github.jpg)](https://github.com/tristandeleu/pytorch-maml-rl)\n* [On First-Order Meta-Learning Algorithms](https://arxiv.org/abs/1803.02999). Alex Nichol, Joshua Achiam, John Schulman.\n[![Code](github.jpg)](https://github.com/openai/supervised-reptile) \n* [Prototypical Networks for Few-shot Learning](https://arxiv.org/abs/1703.05175), Jake Snell, Kevin Swersky, Richard S. Zemel. NIPS 2017. \n[![Code](github.jpg)](https://github.com/jakesnell/prototypical-networks)\n* [Learning to learn by gradient descent by gradient descent](https://arxiv.org/abs/1606.04474), Marcin Andrychowicz, Misha Denil, Sergio Gomez, Matthew W. Hoffman, David Pfau, Tom Schaul, Brendan Shillingford, Nando de Freitas\n[![Code](github.jpg)](https://github.com/deepmind/learning-to-learn) \n[![Code](github.jpg)](https://becominghuman.ai/paper-repro-learning-to-learn-by-gradient-descent-by-gradient-descent-6e504cc1c0de)\n* [Learning to Learn without Gradient Descent by Gradient Descent](http://proceedings.mlr.press/v70/chen17e/chen17e.pdf), Yutian Chen, Matthew W. Hoffman, Sergio Gomez Colmenarejo, Misha Denil, Timothy P. Lillicrap,\nMatt Botvinick, Nando de Freitas, ICML 2017\n* [OPTIMIZATION AS A MODEL FOR FEW-SHOT LEARNING](https://openreview.net/pdf?id=rJY0-Kcll), Sachin Ravi, Hugo Larochelle. ICLR 2017\n[![Code](github.jpg)](https://github.com/twitter/meta-learning-lstm) \n[![Code](github.jpg)](https://github.com/gitabcworld/FewShotLearning) \n* [Meta-SGD: Learning to Learn Quickly for Few-Shot Learning](https://arxiv.org/abs/1707.09835), Zhenguo Li, Fengwei Zhou, Fei Chen, Hang Li\n[![Code](github.jpg)](https://github.com/foolyc/Meta-SGD)\n* [Unsupervised Meta-Learning for Reinforcement Learning](https://arxiv.org/abs/1806.04640). Abhishek Gupta, Benjamin Eysenbach, Chelsea Finn, Sergey Levine.\n* [Learning to Compare: Relation Network for Few-Shot Learning](https://arxiv.org/abs/1711.06025), Flood Sung, Yongxin Yang, Li Zhang, Tao Xiang, Philip H.S. Torr, Timothy M. Hospedales, CVPR 2018\n[Few-shot Pytorch![Code](github.jpg)](https://github.com/floodsung/LearningToCompare_FSL)\n[Zero-shot Pytorch![Code](github.jpg)](https://github.com/lzrobots/LearningToCompare_ZSL)\n[miniImageNet Pytorch![Code](github.jpg)](https://github.com/dragen1860/LearningToCompare-Pytorch)\n* [Object-Level Representation Learning for Few-Shot Image Classification](https://arxiv.org/abs/1805.10777), Liangqu Long, Wei Wang, Jun Wen, Meihui Zhang, Qian Lin, Beng Chin Ooi\n* [A Simple Neural Attentive Meta-Learner](https://arxiv.org/abs/1707.03141), Nikhil Mishra, Mostafa Rohaninejad, Xi Chen, Pieter Abbeel. ICLR 2018\n[![Code](github.jpg)](https://github.com/eambutu/snail-pytorch)\n\n* [Meta-Learning for Semi-Supervised Few-Shot Classification](https://openreview.net/forum?id=HJcSzz-CZ), Mengye Ren, Eleni Triantafillou, Sachin Ravi, Jake Snell, Kevin Swersky, Joshua B. Tenenbaum, Hugo Larochelle, Richard S. Zemel. ICLR 2018\n* [Learning to Optimize](https://arxiv.org/abs/1606.01885), Ke Li, Jitendra Malik\n* [Matching Networks for One Shot Learning](https://arxiv.org/abs/1606.04080), Oriol Vinyals, Charles Blundell, Timothy Lillicrap, Koray Kavukcuoglu, Daan Wierstra\n* [Meta-Learning with Memory-Augmented Neural Networks](http://proceedings.mlr.press/v48/santoro16.pdf), Adam Santoro, Sergey Bartunov, Matthew Botvinick, Daan Wierstra, Timothy Lillicrap\n[![Code](github.jpg)](https://github.com/tristandeleu/ntm-one-shot)\n* [CAML: Fast Context Adaptation via Meta-Learning](https://arxiv.org/abs/1810.03642), Luisa M Zintgraf, Kyriacos Shiarlis, Vitaly Kurin, Katja Hofmann, Shimon Whiteson\n* [Unsupervised Learning via Meta-Learning](https://arxiv.org/pdf/1810.02334.pdf), Kyle Hsu, Sergey Levine, Chelsea Finn\n[![Code](github.jpg)](https://github.com/hsukyle/cactus-maml)\n[![Code](github.jpg)](https://github.com/hsukyle/cactus-protonets)\n* [Fast Parameter Adaptation for Few-shot Image Captioning and Visual Question Answering](http://xuanyidong.com/pdf/FPAIT-MM-18.pdf). Xuanyi Dong, Linchao Zhu, De Zhang, Yi Yang, Fei Wu. [![Code](github.jpg)](https://github.com/D-X-Y/FPAIT)\n\n\n# Tutorials and Slides\n\n* NeuraIPS meta-learning workshop: [2018](http://metalearning.ml/2018/), [2017](http://metalearning.ml/2017/)\n\n* [What’s Wrong with Meta-Learning](http://metalearning.ml/2018/slides/meta_learning_2018_Levine.pdf)\n\n* [Meta-Learning: Learning to Learn Fast](https://lilianweng.github.io/lil-log/2018/11/30/meta-learning.html)\n\n* [How to train your MAML: A step by step approach](https://www.bayeswatch.com/2018/11/30/HTYM/)\n\n* [From zero to research — An introduction to Meta-learning](https://medium.com/huggingface/from-zero-to-research-an-introduction-to-meta-learning-8e16e677f78a)\n* [Deep learning to learn](https://www.dropbox.com/s/j7coq7rz6ig5f6n/2018_08_02_Amazon-SF-ML-Meetup-Abbeel-final.pdf?dl=0). Pieter Abbeel\n* [Meta-Learning Frontiers: Universal, Uncertain, and Unsupervised](http://people.eecs.berkeley.edu/~cbfinn/_files/metalearning_frontiers_2018_small.pdf), Sergey Levine, Chelsea Finn\n\n# Reseachers and Labs\n* [Chelsa Finn](http://people.eecs.berkeley.edu/~cbfinn/), UC Berkeley\n* [Misha Denil](http://mdenil.com/), DeepMind\n* [Sachin Ravi](http://www.cs.princeton.edu/~sachinr/), Princeton University\n* [Hugo Larochelle](https://ai.google/research/people/105144), Google Brain\n* [Jake Snell](http://www.cs.toronto.edu/~jsnell/), University of Toronto, Vector Institute\n* [Adam Santoro](https://scholar.google.com/citations?hl=en\u0026user=evIkDWoAAAAJ\u0026view_op=list_works\u0026sortby=pubdate), DeepMind\n* [JANE X. WANG](http://www.janexwang.com/), DeepMind\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdragen1860%2Fawesome-meta-learning","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdragen1860%2Fawesome-meta-learning","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdragen1860%2Fawesome-meta-learning/lists"}