# Auto-Meta: Automated Gradient Based Meta Learner Search

arXiv: https://arxiv.org/abs/1806.06927 · HTML: https://mlsanity.com/paper/1806.06927/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Jun 2018.

## Built on by (most cited first, 14 of 14)

- [Investigating Bi-Level Optimization for Learning and Vision from a Unified Perspective: A Survey and Beyond](https://mlsanity.com/paper/2101.11517/) (2021)
- [Rapid Neural Architecture Search by Learning to Generate Graphs from Datasets](https://mlsanity.com/paper/2107.00860/) (2021)
- [Global Convergence of MAML and Theory-Inspired Neural Architecture Search for Few-Shot Learning](https://mlsanity.com/paper/2203.09137/) (2022)
- [Learning Symbolic Model-Agnostic Loss Functions via Meta-Learning](https://mlsanity.com/paper/2209.08907/) (2022)
- [SubStrat: A Subset-Based Strategy for Faster AutoML](https://mlsanity.com/paper/2206.03070/) (2022)
- [Meta-ticket: Finding optimal subnetworks for few-shot learning within randomly initialized neural networks](https://mlsanity.com/paper/2205.15619/) (2022)
- [Meta-Learning Adaptive Loss Functions](https://mlsanity.com/paper/2301.13247/) (2023)
- [Rapid Model Architecture Adaption for Meta-Learning](https://mlsanity.com/paper/2109.04925/) (2021)
- [Across-Task Neural Architecture Search via Meta Learning](https://mlsanity.com/paper/2110.05842/) (2021)
- [Meta-Learning of NAS for Few-shot Learning in Medical Image Applications](https://mlsanity.com/paper/2203.08951/) (2022)
- [Subspace Adaptation Prior for Few-Shot Learning](https://mlsanity.com/paper/2310.09028/) (2023)
- [Fast and Efficient Local Search for Genetic Programming Based Loss Function Learning](https://mlsanity.com/paper/2403.00865/) (2024)
- [Where and How to Enhance: Discovering Bit-Width Contribution for Mixed Precision Quantization](https://mlsanity.com/paper/2508.03002/) (2025)
- [Meta-Learning Hyperparameters for Parameter Efficient Fine-Tuning](https://mlsanity.com/paper/2603.01759/) (2026)

## Abstract (arXiv)

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 citeliu:pnasgoogle: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 citefinn: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.