Poster

Subspace Learning for Effective Meta-Learning

Weisen JIANG · James Kwok · Yu Zhang

Hall E #535

Keywords: [ OPT: Bilevel optimization ] [ MISC: Transfer, Multitask and Meta-learning ]

[ Abstract ]
[ Poster [ Paper PDF
Thu 21 Jul 3 p.m. PDT — 5 p.m. PDT
 
Spotlight presentation: Miscellaneous Aspects of Machine Learning
Thu 21 Jul 7:30 a.m. PDT — 9 a.m. PDT

Abstract:

Meta-learning aims to extract meta-knowledge from historical tasks to accelerate learning on new tasks. Typical meta-learning algorithms like MAML learn a globally-shared meta-model for all tasks. However, when the task environments are complex, task model parameters are diverse and a common meta-model is insufficient to capture all the meta-knowledge. To address this challenge, in this paper, task model parameters are structured into multiple subspaces, and each subspace represents one type of meta-knowledge. We propose an algorithm to learn the meta-parameters (\ie, subspace bases). We theoretically study the generalization properties of the learned subspaces. Experiments on regression and classification meta-learning datasets verify the effectiveness of the proposed algorithm.

Chat is not available.