Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
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.
Code (85)
Tasks
Category-Agnostic Pose EstimationFew-Shot Image ClassificationFew-Shot LearningGeneral Classificationimage-classificationImage ClassificationMeta-LearningOne-Shot Learningregressionreinforcement-learningReinforcement LearningReinforcement Learning (RL)Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Unraveling Model-Agnostic Meta-Learning via The Adaptation Learning Rate
Model-Agnostic Meta-Learning (MAML) aims to find initial weights that allow fast adaptation to new tasks. The adaptation (inner loop) learning rate in MAML plays a central role in enabling such fast adaptation. However, …
Meta-LearningModel-Agnostic Meta-Learning using Runge-Kutta Methods
Meta-learning has emerged as an important framework for learning new tasks from just a few examples. The success of any meta-learning model depends on (i) its fast adaptation to new tasks, as well as (ii) having a shared…
Meta-LearningmodelReinforcement LearningMeta-Learning for Fast Cross-Lingual Adaptation in Dependency Parsing
Meta-learning, or learning to learn, is a technique that can help to overcome resource scarcity in cross-lingual NLP problems, by enabling fast adaptation to new tasks. We apply model-agnostic meta-learning (MAML) to the…
Dependency ParsingFew-Shot LearningMeta-LearningFaster Optimization-Based Meta-Learning Adaptation Phase
Neural networks require a large amount of annotated data to learn. Meta-learning algorithms propose a way to decrease the number of training samples to only a few. One of the most prominent optimization-based meta-learni…
Meta-LearningOn the Importance of Attention in Meta-Learning for Few-Shot Text Classification
Current deep learning based text classification methods are limited by their ability to achieve fast learning and generalization when the data is scarce. We address this problem by integrating a meta-learning procedure t…
ClassificationFew-Shot Text ClassificationGeneral ClassificationInductive Bias+7