Generalized Inner Loop Meta-Learning

Edward Grefenstette, Brandon Amos, Denis Yarats, Phu Mon Htut, Artem Molchanov +4 more
10/3/2019
cs.LGstat.ML

Official code: learnables/learn2learn (2,893 stars, MIT, PyTorch, last commit 2025-12-16). 1 more implementation below.

Abstract

Many (but not all) approaches self-qualifying as "meta-learning" in deep learning and reinforcement learning fit a common pattern of approximating the solution to a nested optimization problem. In this paper, we give a formalization of this shared pattern, which we call GIMLI, prove its general requirements, and derive a general-purpose algorithm for implementing similar approaches. Based on this analysis and algorithm, we describe a library of our design, higher, which we share with the community to assist and enable future research into these kinds of meta-learning approaches. We end the paper by showcasing the practical applications of this framework and library through illustrative experiments and ablation studies which they facilitate.

View on arXivView PDF

Code Implementations(2)

learnables/learn2learnOfficial100%
PyTorchMIT

A PyTorch Library for Meta-learning Research

2,893358Cython, PythonAug 8, 201910 months agoMIT
few-shotfinetuninglearn2learnlearning2learnmaml+6 more
facebookresearch/higherOfficial100%
Apache-2.0

higher is a pytorch library allowing users to obtain higher order gradients over losses spanning training loops rather than individual training steps.

1,624125PythonSep 6, 20194 years agoApache-2.0

Similar Papers

A Tutorial on Meta-Reinforcement Learning

88% match2023

Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks

86% match2 repos2.7k2017

Meta-Learning and Meta-Reinforcement Learning - Tracing the Path towards DeepMind's Adaptive Agent

85% match2026

Learning Action Translator for Meta Reinforcement Learning on Sparse-Reward Tasks

85% match2022

Meta Reinforcement Learning with Task Embedding and Shared Policy

85% match1 repo352019

Meta Reinforcement Learning with Successor Feature Based Context

85% match2022

Cite this paper

@article{grefenstette2019generalized,
  title  = {Generalized Inner Loop Meta-Learning},
  author = {Edward Grefenstette and Brandon Amos and Denis Yarats and Phu Mon Htut and Artem Molchanov and Franziska Meier and Douwe Kiela and Kyunghyun Cho and Soumith Chintala},
  year   = {2019},
  eprint = {1910.01727},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1910.01727}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1910.01727.svg)](https://codeofpaper.com/paper/1910.01727)

Discussion