Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks

Code

• github.com/cbfinn/maml_rl
  OfficialIn papertf★ 0
• github.com/cbfinn/maml
  OfficialIn papertf★ 0
• github.com/learnables/learn2learn
  pytorch★ 2,878
• github.com/leopard-ai/betty
  pytorch★ 346
• github.com/JWSoh/MZSR
  tf★ 277
• github.com/fmu2/PyTorch-MAML
  pytorch★ 247
• github.com/shaohua0116/MultiDigitMNIST
  none★ 103
• github.com/prajjwal1/fluence
  pytorch★ 70
• github.com/MoritzTaylor/maml-rl-tf2
  tf★ 27
• github.com/mikehuisman/revisiting-learned-optimizers
  pytorch★ 5

Abstract

We propose an algorithm for meta-learning that is model-agnostic, in the sense that it is compatible with any model trained with gradient descent and applicable to a variety of different learning problems, including classification, regression, and reinforcement learning. The goal of meta-learning is to train a model on a variety of learning tasks, such that it can solve new learning tasks using only a small number of training samples. In our approach, the parameters of the model are explicitly trained such that a small number of gradient steps with a small amount of training data from a new task will produce good generalization performance on that task. In effect, our method trains the model to be easy to fine-tune. We demonstrate that this approach leads to state-of-the-art performance on two few-shot image classification benchmarks, produces good results on few-shot regression, and accelerates fine-tuning for policy gradient reinforcement learning with neural network policies.

Tasks

Benchmark Results

Reproductions