Auto-Meta: Automated Gradient Based Meta Learner Search

TL;DR

This paper introduces Auto-Meta, a method that automates the design of gradient-based meta-learners using neural architecture search, achieving state-of-the-art results on few-shot learning tasks.

Contribution

It is the first to successfully apply neural architecture search to optimize meta-learner architectures, significantly improving performance.

Findings

Achieved 74.65% accuracy on 5-shot 5-way Mini-ImageNet classification

Outperformed MAML by 11.54%

First neural architecture search implementation in meta learning

Abstract

Fully automating machine learning pipelines is one of the key challenges of current artificial intelligence research, since practical machine learning often requires costly and time-consuming human-powered processes such as model design, algorithm development, and hyperparameter tuning. In this paper, we verify that automated architecture search synergizes with the effect of gradient-based meta learning. We adopt the progressive neural architecture search \cite{liu:pnas_google:DBLP:journals/corr/abs-1712-00559} to find optimal architectures for meta-learners. The gradient based meta-learner whose architecture was automatically found achieved state-of-the-art results on the 5-shot 5-way Mini-ImageNet classification problem with $74.65\%$ accuracy, which is $11.54\%$ improvement over the result obtained by the first gradient-based meta-learner called MAML \cite{finn:maml:DBLP:conf/icml/FinnAL17}. To our best knowledge, this work is the first successful neural architecture search implementation in the context of meta learning.