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

Source: [MetaMix: Improved Meta-Learning with Interpolation-based Consistency Regularization](<https://www.sota2.com/research/paper/68fa68851e209131cea1ca30>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T22:38:59.898Z

Authors: Yangbin Chen, Yun Ma, Tom Ko, Jianping Wang, Qing Li

Published: 2020-09-29T02:44:13.000Z

## Abstract

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.

## 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.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2009.13735>)

[PDF](<https://arxiv.org/pdf/2009.13735.pdf>)