learn2learn: A Library for Meta-Learning Research

Abstract

Meta-learning researchers face two fundamental issues in their empirical work: prototyping and reproducibility. Researchers are prone to make mistakes when prototyping new algorithms and tasks because modern meta-learning methods rely on unconventional functionalities of machine learning frameworks. In turn, reproducing existing results becomes a tedious endeavour -- a situation exacerbated by the lack of standardized implementations and benchmarks. As a result, researchers spend inordinate amounts of time on implementing software rather than understanding and developing new ideas. This manuscript introduces learn2learn, a library for meta-learning research focused on solving those prototyping and reproducibility issues. learn2learn provides low-level routines common across a wide-range of meta-learning techniques (e.g. meta-descent, meta-reinforcement learning, few-shot learning), and builds standardized interfaces to algorithms and benchmarks on top of them. In releasing learn2learn under a free and open source license, we hope to foster a community around standardized software for meta-learning research.

Software available at: https://github.com/learnables/learn2learn

References in corpus (14)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Language Models are Few-Shot Learners
• Benchmarking Deep Reinforcement Learning for Continuous Control
• Meta-SGD: Learning to Learn Quickly for Few-Shot Learning
• RLlib: Abstractions for Distributed Reinforcement Learning
• Meta-Gradient Reinforcement Learning
• Differentiable Convex Optimization Layers
• Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learning
• Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAML
• Online Learning Rate Adaptation with Hypergradient Descent
• Torchmeta: A Meta-Learning library for PyTorch
• Using learned optimizers to make models robust to input noise
• ProMP: Proximal Meta-Policy Search

Cited by in corpus (6)

• When MAML Can Adapt Fast and How to Assist When It Cannot
• Blinder: End-to-end Privacy Protection in Sensing Systems via Personalized Federated Learning
• MetaHDR: Model-Agnostic Meta-Learning for HDR Image Reconstruction
• On sensitivity of meta-learning to support data
• Online Bilevel Optimization: Regret Analysis of Online Alternating Gradient Methods
• Uniform Sampling over Episode Difficulty