Previous works on meta-learning either relied on elaborately hand-designed network structures or adopted specialized learning rules to a particular domain. We propose a universal framework to optimize the meta-learning process automatically by adopting neural architecture search technique (NAS). NAS automatically generates and evaluates meta-learner's architecture for few-shot learning problems, while the meta-learner uses meta-learning algorithm to optimize its parameters based on the distribution of learning tasks. Parameter sharing and experience replay are adopted to accelerate the architectures searching process, so it takes only 1-2 GPU days to find good architectures. Extensive experiments on Mini-ImageNet and Omniglot show that our algorithm excels in few-shot learning tasks. The best architecture found on Mini-ImageNet achieves competitive results when transferred to Omniglot, which shows the high transferability of architectures among different computer vision problems.
@article{arxiv.1909.03817,
title = {Efficient Automatic Meta Optimization Search for Few-Shot Learning},
author = {Xinyue Zheng and Peng Wang and Qigang Wang and Zhongchao shi and Feiyu Xu},
journal= {arXiv preprint arXiv:1909.03817},
year = {2019}
}