Probabilistic Model-Agnostic Meta-Learning

06/07/2018
by   Chelsea Finn, et al.
0

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.

READ FULL TEXT
research
03/04/2020

Meta Cyclical Annealing Schedule: A Simple Approach to Avoiding Meta-Amortization Error

The ability to learn new concepts with small amounts of data is a crucia...
research
06/08/2023

EMO: Episodic Memory Optimization for Few-Shot Meta-Learning

Few-shot meta-learning presents a challenge for gradient descent optimiz...
research
03/02/2023

Model agnostic methods meta-learn despite misspecifications

Due to its empirical success on few shot classification and reinforcemen...
research
05/24/2018

Decision-Theoretic Meta-Learning: Versatile and Efficient Amortization of Few-Shot Learning

This paper develops a general framework for data efficient and versatile...
research
05/31/2022

HyperMAML: Few-Shot Adaptation of Deep Models with Hypernetworks

The aim of Few-Shot learning methods is to train models which can easily...
research
05/12/2021

Exploring the Similarity of Representations in Model-Agnostic Meta-Learning

In past years model-agnostic meta-learning (MAML) has been one of the mo...

Please sign up or login with your details

Forgot password? Click here to reset