# Auto-Meta: Automated Gradient Based Meta Learner Search Source: [Auto-Meta: Automated Gradient Based Meta Learner Search]() Collection index: [llms.txt]() Data updated: 2025-10-25T21:20:52.699Z Authors: Jaehong Kim, Sangyeul Lee, Sungwan Kim, Moonsu Cha, Jung Kwon Lee, Youngduck Choi, Yongseok Choi, Dong-Yeon Cho, Jiwon Kim Published: 2018-06-11T04:28:02.000Z ## 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [5-way Few-Shot Classification Accuracy on miniImageNet (test)](): 5-way Classification; miniImageNet (test); Accuracy: not recorded. ## Original sources and implementation [Original paper]() [PDF]()