How to train your MAML

By Antreas Antoniou, Harrison Edwards, Amos J. Storkey. International Conference on Learning Representations, 2018

887 citations recorded by the source corpus.

The field of few-shot learning has recently seen substantial advancements. Most of these advancements came from casting few-shot learning as a meta-learning problem. Model Agnostic Meta Learning or MAML is currently one of the best approaches for few-shot learning via meta-learning. MAML is simple, elegant and very powerful, however, it has a variety of issues, such as being very sensitive to neural network architectures, often leading to instability during training, requiring arduous hyperparameter searches to stabilize training and achieve high generalization and being very computationally expensive at both training and inference times. In this paper, we propose various modifications to MAML that not only stabilize the system, but also substantially improve the generalization performance, convergence speed and computational overhead of MAML, which we call MAML++.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Meta & Continual Learning

View Paper: https://arxiv.org/abs/1810.09502

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Sergey Levine
  2. Yoshua Bengio
  3. Mohit Bansal
  4. Dacheng Tao
  5. Bernt Schiele
  6. Han-Jia Ye
  7. Jianfeng Gao
  8. Percy Liang

In Computer Vision and Pattern Recognition

  1. Luc Van Gool
  2. Dacheng Tao
  3. Bernt Schiele
  4. Trevor Darrell
  5. Ming-Hsuan Yang
  6. Xiaogang Wang
  7. Jitendra Malik
  8. Yi Yang

In Meta & Continual Learning

  1. Han-Jia Ye
  2. De-chuan Zhan
  3. Wei-Lun Chao
  4. Da-Wei Zhou
  5. Bernt Schiele
  6. Chelsea Finn
  7. Qianru Sun
  8. Yaoyao Liu

Citations in the corpus