Model-Agnostic Learning to Meta-Learn

被引：0

作者：

Devos, Arnout ^{[1
]}

Dandi, Yatin ^{[1
,2
]}

机构：

[1] Ecole Polytech Fed Lausanne, Sch Comp & Commun Sci, Lausanne, Switzerland

[2] IIT Kanpur, Dept Comp Sci & Engn, Kanpur, Uttar Pradesh, India

来源：

NEURIPS 2020 WORKSHOP ON PRE-REGISTRATION IN MACHINE LEARNING, VOL 148 | 2020年 / 148卷

关键词：

Pre-registration; Machine Learning;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper, we propose a learning algorithm that enables a model to quickly exploit commonalities among related tasks from an unseen task distribution, before quickly adapting to specific tasks from that same distribution. We investigate how learning with different task distributions can first improve adaptability by meta-finetuning on related tasks before improving goal task generalization with finetuning. Synthetic regression experiments validate the intuition that learning to meta-learn improves adaptability and consecutively generalization. Experiments on more complex image classification, continual regression, and reinforcement learning tasks demonstrate that learning to meta-learn generally improves task-specific adaptation. The methodology, setup, and hypotheses in this proposal were positively evaluated by peer review before conclusive experiments were carried out.

引用

页码：155 / 175

页数：21