# MetaMix: Improved Meta-Learning with Interpolation-based Consistency Regularization

arXiv: https://arxiv.org/abs/2009.13735 · HTML: https://mlsanity.com/paper/2009.13735/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Sep 2020.

## Built on by (most cited first, 5 of 5)

- [A Survey of Mix-based Data Augmentation: Taxonomy, Methods, Applications, and Explainability](https://mlsanity.com/paper/2212.10888/) (2022)
- [GCT: Graph Co-Training for Semi-Supervised Few-Shot Learning](https://mlsanity.com/paper/2203.07738/) (2022)
- [DAC-MR: Data Augmentation Consistency Based Meta-Regularization for Meta-Learning](https://mlsanity.com/paper/2305.07892/) (2023)
- [Meta-Task: A Method-Agnostic Framework for Learning to Regularize in Few-Shot Learning](https://mlsanity.com/paper/2402.18599/) (2024)
- [Reducing Variance in Meta-Learning via Laplace Approximation for Regression Tasks](https://mlsanity.com/paper/2410.01476/) (2024)

## Abstract (arXiv)

Model-Agnostic Meta-Learning (MAML) and its variants are popular few-shot classification methods. They train an initializer across a variety of sampled learning tasks (also known as episodes) such that the initialized model can adapt quickly to new tasks. However, current MAML-based algorithms have limitations in forming generalizable decision boundaries. In this paper, we propose an approach called MetaMix. It generates virtual feature-target pairs within each episode to regularize the backbone models. MetaMix can be integrated with any of the MAML-based algorithms and learn the decision boundaries generalizing better to new tasks. Experiments on the mini-ImageNet, CUB, and FC100 datasets show that MetaMix improves the performance of MAML-based algorithms and achieves state-of-the-art result when integrated with Meta-Transfer Learning.