# Meta-learning autoencoders for few-shot prediction

arXiv: https://arxiv.org/abs/1807.09912 · HTML: https://mlsanity.com/paper/1807.09912/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Jul 2018.

## Built on by (most cited first, 7 of 7)

- [The Internet of Federated Things (IoFT): A Vision for the Future and In-depth Survey of Data-driven Approaches for Federated Learning](https://mlsanity.com/paper/2111.05326/) (2021)
- [Compositional Law Parsing with Latent Random Functions](https://mlsanity.com/paper/2209.09115/) (2022)
- [Tailored Forecasting from Short Time Series via Meta-learning](https://mlsanity.com/paper/2501.16325/) (2025)
- [A Meta-learning Approach to Reservoir Computing: Time Series Prediction with Limited Data](https://mlsanity.com/paper/2110.03722/) (2021)
- [A Framework of Meta Functional Learning for Regularising Knowledge Transfer](https://mlsanity.com/paper/2203.14840/) (2022)
- [AutoProtoNet: Interpretability for Prototypical Networks](https://mlsanity.com/paper/2204.00929/) (2022)
- [Smooth Mathematical Function from Compact Neural Networks](https://mlsanity.com/paper/2301.00181/) (2022)

## Abstract (arXiv)

Compared to humans, machine learning models generally require significantly more training examples and fail to extrapolate from experience to solve previously unseen challenges. To help close this performance gap, we augment single-task neural networks with a meta-recognition model which learns a succinct model code via its autoencoder structure, using just a few informative examples. The model code is then employed by a meta-generative model to construct parameters for the task-specific model. We demonstrate that for previously unseen tasks, without additional training, this Meta-Learning Autoencoder (MeLA) framework can build models that closely match the true underlying models, with loss significantly lower than given by fine-tuned baseline networks, and performance that compares favorably with state-of-the-art meta-learning algorithms. MeLA also adds the ability to identify influential training examples and predict which additional data will be most valuable to acquire to improve model prediction.