On the Subspace Structure of Gradient-Based Meta-Learning

2022/07/08 by Tegnér, Gustaf, Reichlin, Alfredo, Yin, Hang +2
#FOS: Computer and information sciences #Machine Learning (cs.LG)

paper · doi:10.48550/arxiv.2207.03804

Abstract

In this work we provide an analysis of the distribution of the post-adaptation parameters of Gradient-Based Meta-Learning (GBML) methods. Previous work has noticed how, for the case of image-classification, this adaptation only takes place on the last layers of the network. We propose the more general notion that parameters are updated over a low-dimensional subspace of the same dimensionality as the task-space and show that this holds for regression as well. Furthermore, the induced subspace structure provides a method to estimate the intrinsic dimension of the space of tasks of common few-shot learning datasets.

Related

• Gradient-Based Meta-Learning with Learned Layerwise Metric and Subspace
• Subspace Adaptation Prior for Few-Shot Learning
• Towards Understanding Generalization in Gradient-Based Meta-Learning
• Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation
• Regularizing Meta-Learning via Gradient Dropout