Probabilistic Model-Agnostic Meta-Learning

Abstract

Meta-learning for few-shot learning entails acquiring a prior over previous tasks and experiences, such that new tasks be learned from small amounts of data. However, a critical challenge in few-shot learning is task ambiguity: even when a powerful prior can be meta-learned from a large number of prior tasks, a small dataset for a new task can simply be too ambiguous to acquire a single model (e.g., a classifier) for that task that is accurate. In this paper, we propose a probabilistic meta-learning algorithm that can sample models for a new task from a model distribution. Our approach extends model-agnostic meta-learning, which adapts to new tasks via gradient descent, to incorporate a parameter distribution that is trained via a variational lower bound. At meta-test time, our algorithm adapts via a simple procedure that injects noise into gradient descent, and at meta-training time, the model is trained such that this stochastic adaptation procedure produces samples from the approximate model posterior. Our experimental results show that our method can sample plausible classifiers and regressors in ambiguous few-shot learning problems. We also show how reasoning about ambiguity can also be used for downstream active learning problems.

arXiv commentNeurIPS 2018. First two authors contributed equally. Supplementary results available at https://sites.google.com/view/probabilistic-maml/

References in corpus (17)

• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Prototypical Networks for Few-shot Learning
• Stochastic Backpropagation and Approximate Inference in Deep Generative Models
• Weight Uncertainty in Neural Networks
• Matching Networks for One Shot Learning
• A Simple Neural Attentive Meta-Learner
• Meta-SGD: Learning to Learn Quickly for Few-Shot Learning
• RL${}^2$: Fast Reinforcement Learning via Slow Reinforcement Learning
• Few-Shot Learning with Graph Neural Networks
• One-Shot Visual Imitation Learning via Meta-Learning
• Composing graphical models with neural networks for structured representations and fast inference
• Bayesian Recurrent Neural Networks
• Early Visual Concept Learning with Unsupervised Deep Learning
• Meta-Learning and Universality: Deep Representations and Gradient Descent can Approximate any Learning Algorithm
• Bayesian Multitask Learning with Latent Hierarchies
• Amortized Inference Regularization
• Deep Prior

Cited by in corpus (9)

• Meta-Learning with Latent Embedding Optimization
• The effects of negative adaptation in Model-Agnostic Meta-Learning
• Meta-Learning surrogate models for sequential decision making
• Exploring hyper-parameter spaces of neuroscience models on high performance computers with Learning to Learn
• Online Structured Meta-learning
• Non-Gaussian Gaussian Processes for Few-Shot Regression
• Information-Theoretic Analysis of Epistemic Uncertainty in Bayesian Meta-learning
• ST-MAML: A Stochastic-Task based Method for Task-Heterogeneous Meta-Learning
• Population-Based Evolution Optimizes a Meta-Learning Objective