Auto-Meta: Automated Gradient Based Meta Learner Search
This work addresses the problem of costly human intervention in ML for researchers and practitioners, representing an incremental advance by applying existing search methods to meta-learning.
The paper tackles automating machine learning pipelines by combining automated architecture search with gradient-based meta-learning, achieving state-of-the-art results with 74.65% accuracy on the 5-shot 5-way Mini-ImageNet classification, an 11.54% improvement over MAML.
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.