Multi-Subspace Meta-Learning

doi:10.1016/j.artint.2026.104626

Multi-Subspace Meta-Learning

2026-09-25

0

PRE

AI

DOI：10.1016/j.artint.2026.104626

Original

Original request for help

Save

Abstract

En 中文

Meta-learning, which extracts meta-knowledge from historical tasks to facilitate learning new tasks, has achieved great success in various applications. Representative meta-learning algorithms like MAML assume tasks are similar and propose to learn a globally-shared meta-initialization for all tasks. However, real-world environments are usually complex, making task model parameters diverse and a single meta-initialization is insufficient to capture all the meta-knowledge. To deal with this challenge, we propose multi-subspace meta-learning in this paper. Task model parameters are structured into multiple subspaces, and each subspace represents one type of meta-knowledge. We propose two novel algorithms MUSML and PE-MUSML to learn the meta-parameters (i.e., subspace bases) and theoretically establish the generalization bound of the learned subspaces. Extensive experiments on regression and classification benchmark datasets demonstrate the effectiveness of subspace meta-learning.

Keywords:

meta-learning

subspace learning

few-shot learning

parameter-efficient finetuning

meta-initialization

Multi-Subspace Meta-Learning

Abstract

Journal

Organization

Cited Papers