On Data Efficiency of Meta-learning

Abstract

Meta-learning has enabled learning statistical models that can be quickly adapted to new prediction tasks. Motivated by use-cases in personalized federated learning, we study the often overlooked aspect of the modern meta-learning algorithms -- their data efficiency. To shed more light on which methods are more efficient, we use techniques from algorithmic stability to derive bounds on the transfer risk that have important practical implications, indicating how much supervision is needed and how it must be allocated for each method to attain the desired level of generalization. Further, we introduce a new simple framework for evaluating meta-learning methods under a limit on the available supervision, conduct an empirical study of MAML, Reptile, and Protonets, and demonstrate the differences in the behavior of these methods on few-shot and federated learning benchmarks. Finally, we propose active meta-learning, which incorporates active data selection into learning-to-learn, leading to better performance of all methods in the limited supervision regime.

Preliminary version. An updated version is to appear in AISTATS 2021

References in corpus (17)

• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Prototypical Networks for Few-shot Learning
• Communication-Efficient Learning of Deep Networks from Decentralized Data
• Theoretical Models of Learning to Learn
• Meta-SGD: Learning to Learn Quickly for Few-Shot Learning
• On First-Order Meta-Learning Algorithms
• Improving Federated Learning Personalization via Model Agnostic Meta Learning
• LEAF: A Benchmark for Federated Settings
• Federated Meta-Learning with Fast Convergence and Efficient Communication
• A Closer Look at Few-shot Classification
• Fast Context Adaptation via Meta-Learning
• Online Meta-Learning
• Diverse mini-batch Active Learning
• Salvaging Federated Learning by Local Adaptation
• Learning Algorithms for Active Learning
• Learning-to-Learn Stochastic Gradient Descent with Biased Regularization
• On the Outsized Importance of Learning Rates in Local Update Methods