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.

Papers and Code

• 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.

• 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.

• On First-Order Meta-Learning Algorithms. Alex Nichol, Joshua Achiam, John Schulman.

• Prototypical Networks for Few-shot Learning, Jake Snell, Kevin Swersky, Richard S. Zemel. NIPS 2017.

• 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

• 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

• Meta-SGD: Learning to Learn Quickly for Few-Shot Learning, Zhenguo Li, Fengwei Zhou, Fei Chen, Hang Li

• 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 Zero-shot Pytorch miniImageNet Pytorch

• 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

• 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

• 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

• Fast Parameter Adaptation for Few-shot Image Captioning and Visual Question Answering. Xuanyi Dong, Linchao Zhu, De Zhang, Yi Yang, Fei Wu.

Tutorials and Slides

• 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

Reseachers and Labs

• Chelsa Finn, UC Berkeley
• Misha Denil, DeepMind
• Sachin Ravi, Princeton University
• Hugo Larochelle, Google Brain
• Jake Snell, University of Toronto, Vector Institute
• Adam Santoro, DeepMind
• JANE X. WANG, DeepMind