A curated list of Meta-Learning resources. Inspired by awesome-deep-vision, awesome-adversarial-machine-learning, awesome-deep-learning-papers, and awesome-architecture-search.
Please feel free to pull requests or open an issue to add papers.
Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples. Eleni Triantafillou, Tyler Zhu, Vincent Dumoulin, Pascal Lamblin, Kelvin Xu, Ross Goroshin, Carles Gelada, Kevin Swersky, Pierre-Antoine Manzagol, Hugo Larochelle.
Gradient-Based Meta-Learning with Learned Layerwise Metric and Subspace. Yoonho Lee, Seungjin Choi.
FIGR: Few-shot Image Generation with Reptile. Louis Clouâtre, Marc Demers.
Online gradient-based mixtures for transfer modulation in meta-learning. Ghassen Jerfel, Erin Grant, Thomas L. Griffiths, Katherine Heller.
Auto-Meta: Automated Gradient Based Meta Learner Search. Jaehong Kim, Youngduck Choi, Moonsu Cha, Jung Kwon Lee, Sangyeul Lee, Sungwan Kim, Yongseok Choi, Jiwon Kim.
MetaGAN: An Adversarial Approach to Few-Shot Learning. ZHANG, Ruixiang and Che, Tong and Ghahramani, Zoubin and Bengio, Yoshua and Song, Yangqiu.
Learned Optimizers that Scale and Generalize. Olga Wichrowska, Niru Maheswaranathan, Matthew W. Hoffman, Sergio Gomez Colmenarejo, Misha Denil, Nando de Freitas, Jascha Sohl-Dickstein.
Guiding Policies with Language via Meta-Learning. John D. Co-Reyes, Abhishek Gupta, Suvansh Sanjeev, Nick Altieri, John DeNero, Pieter Abbeel, Sergey Levine.
Deep Comparison: Relation Columns for Few-Shot Learning. Xueting Zhang, Flood Sung, Yuting Qiang, Yongxin Yang, Timothy M. Hospedales.
Towards learning-to-learn. Benjamin James Lansdell, Konrad Paul Kording.
Learning to Learn with Gradients. Finn, Chelsea.
How to train your MAML. Antreas Antoniou, Harrison Edwards, Amos Storkey.
Learned optimizers that outperform SGD on wall-clock and validation loss. Luke Metz, Niru Maheswaranathan, Jeremy Nixon, C. Daniel Freeman, Jascha Sohl-Dickstein
Gradient Agreement as an Optimization Objective for Meta-Learning. Amir Erfan Eshratifar, David Eigen, Massoud Pedram.
Few-Shot Image Recognition by Predicting Parameters from Activations. Siyuan Qiao, Chenxi Liu, Wei Shen, Alan Yuille. CVPR 2018.
[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-84GZKEig-1576313684528)(github.jpg)]
META-LEARNING WITH LATENT EMBEDDING OPTIMIZATION. Andrei A. Rusu, Dushyant Rao, Jakub Sygnowski, Oriol Vinyals, Razvan Pascanu, Simon Osindero & Raia Hadsell
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks, Chelsea Finn, Pieter Abbeel, Sergey Levine. ICML 2017.
[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-LuWO1zyr-1576313684528)(github.jpg)] [外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-kr7KFMcB-1576313684528)(github.jpg)] [外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-hrjAjBAX-1576313684529)(github.jpg)] [外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-u2mn2Gil-1576313684529)(github.jpg)]
On First-Order Meta-Learning Algorithms. Alex Nichol, Joshua Achiam, John Schulman.
[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-Huf6iSSO-1576313684530)(github.jpg)]
Prototypical Networks for Few-shot Learning, Jake Snell, Kevin Swersky, Richard S. Zemel. NIPS 2017.
[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-05MTeVJi-1576313684530)(github.jpg)]
Learning to learn by gradient descent by gradient descent, Marcin Andrychowicz, Misha Denil, Sergio Gomez, Matthew W. Hoffman, David Pfau, Tom Schaul, Brendan Shillingford, Nando de Freitas
(github.jpg)]](https://github.com/deepmind/learning-to-learn)
(github.jpg)]](https://becominghuman.ai/paper-repro-learning-to-learn-by-gradient-descent-by-gradient-descent-6e504cc1c0de)
Learning to Learn without Gradient Descent by Gradient Descent, Yutian Chen, Matthew W. Hoffman, Sergio Gomez Colmenarejo, Misha Denil, Timothy P. Lillicrap,
Matt Botvinick, Nando de Freitas, ICML 2017
OPTIMIZATION AS A MODEL FOR FEW-SHOT LEARNING, Sachin Ravi, Hugo Larochelle. ICLR 2017
[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-dfsgaAGH-1576313684531)(github.jpg)]
[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-sbKm6zVr-1576313684531)(github.jpg)]
Meta-SGD: Learning to Learn Quickly for Few-Shot Learning, Zhenguo Li, Fengwei Zhou, Fei Chen, Hang Li
[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-3nswZMoz-1576313684532)(github.jpg)]
Unsupervised Meta-Learning for Reinforcement Learning. Abhishek Gupta, Benjamin Eysenbach, Chelsea Finn, Sergey Levine.
Learning to Compare: Relation Network for Few-Shot Learning, Flood Sung, Yongxin Yang, Li Zhang, Tao Xiang, Philip H.S. Torr, Timothy M. Hospedales, CVPR 2018
Few-shot Pytorch[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-ciyXQ0sT-1576313684532)(github.jpg)]
Zero-shot Pytorch[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-fmfpwIPF-1576313684532)(github.jpg)]
miniImageNet Pytorch[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-fh2szE8z-1576313684533)(github.jpg)]
Object-Level Representation Learning for Few-Shot Image Classification, Liangqu Long, Wei Wang, Jun Wen, Meihui Zhang, Qian Lin, Beng Chin Ooi
A Simple Neural Attentive Meta-Learner, Nikhil Mishra, Mostafa Rohaninejad, Xi Chen, Pieter Abbeel. ICLR 2018
[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-sbp7IeB8-1576313684533)(github.jpg)]
Meta-Learning for Semi-Supervised Few-Shot Classification, Mengye Ren, Eleni Triantafillou, Sachin Ravi, Jake Snell, Kevin Swersky, Joshua B. Tenenbaum, Hugo Larochelle, Richard S. Zemel. ICLR 2018
Learning to Optimize, Ke Li, Jitendra Malik
Matching Networks for One Shot Learning, Oriol Vinyals, Charles Blundell, Timothy Lillicrap, Koray Kavukcuoglu, Daan Wierstra
Meta-Learning with Memory-Augmented Neural Networks, Adam Santoro, Sergey Bartunov, Matthew Botvinick, Daan Wierstra, Timothy Lillicrap
[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-pVXNpC6i-1576313684533)(github.jpg)]
CAML: Fast Context Adaptation via Meta-Learning, Luisa M Zintgraf, Kyriacos Shiarlis, Vitaly Kurin, Katja Hofmann, Shimon Whiteson
Unsupervised Learning via Meta-Learning, Kyle Hsu, Sergey Levine, Chelsea Finn
[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-hOQCvJDv-1576313684534)(github.jpg)]
[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-S9Vept2t-1576313684534)(github.jpg)]
Fast Parameter Adaptation for Few-shot Image Captioning and Visual Question Answering. Xuanyi Dong, Linchao Zhu, De Zhang, Yi Yang, Fei Wu. [外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-VybKZBfx-1576313684534)(github.jpg)]
NeuraIPS meta-learning workshop: 2018, 2017
What’s Wrong with Meta-Learning
Meta-Learning: Learning to Learn Fast
How to train your MAML: A step by step approach
From zero to research — An introduction to Meta-learning
Deep learning to learn. Pieter Abbeel
Meta-Learning Frontiers: Universal, Uncertain, and Unsupervised, Sergey Levine, Chelsea Finn