Meta-SGD: Learning to Learn Quickly for Few-Shot Learning

Code

• github.com/myungsub/meta-interpolation
  pytorch★ 80
• github.com/tobiasvanderwerff/MetaHTR
  pytorch★ 13
• github.com/ash3n/Meta-Gradients
  tf★ 0
• github.com/llan-ml/tesp
  tf★ 0
• github.com/ash3n/Meta-SGD-TF
  tf★ 0
• github.com/foolyc/Meta-SGD
  tf★ 0
• github.com/ash3n/Meta-SGD
  tf★ 0
• github.com/BBDrive/Meta-SGD-RL
  pytorch★ 0

Abstract

Few-shot learning is challenging for learning algorithms that learn each task in isolation and from scratch. In contrast, meta-learning learns from many related tasks a meta-learner that can learn a new task more accurately and faster with fewer examples, where the choice of meta-learners is crucial. In this paper, we develop Meta-SGD, an SGD-like, easily trainable meta-learner that can initialize and adapt any differentiable learner in just one step, on both supervised learning and reinforcement learning. Compared to the popular meta-learner LSTM, Meta-SGD is conceptually simpler, easier to implement, and can be learned more efficiently. Compared to the latest meta-learner MAML, Meta-SGD has a much higher capacity by learning to learn not just the learner initialization, but also the learner update direction and learning rate, all in a single meta-learning process. Meta-SGD shows highly competitive performance for few-shot learning on regression, classification, and reinforcement learning.

Tasks

Benchmark Results

Reproductions