Gradient-based meta-learning techniques are both widely applicable and proficient at solving challenging few-shot learning and fast adaptation problems. However, they have practical difficulties when operating on high-dimensional parameter spaces in extreme low-data regimes. We show that it is possible to bypass these limitations by learning a data-dependent latent generative representation of model parameters, and performing gradient-based meta-learning in this low-dimensional latent space. The resulting approach, latent embedding optimization (LEO), decouples the gradient-based adaptation procedure from the underlying high-dimensional space of model parameters. Our evaluation shows that LEO can achieve state-of-the-art performance on the competitive miniImageNet and tieredImageNet few-shot classification tasks. Further analysis indicates LEO is able to capture uncertainty in the data, and can perform adaptation more effectively by optimizing in latent space.
@article{arxiv.1807.05960,
title = {Meta-Learning with Latent Embedding Optimization},
author = {Andrei A. Rusu and Dushyant Rao and Jakub Sygnowski and Oriol Vinyals and Razvan Pascanu and Simon Osindero and Raia Hadsell},
journal= {arXiv preprint arXiv:1807.05960},
year = {2019}
}