# MetaMixUp: Learning Adaptive Interpolation Policy of MixUp with Meta-Learning

arXiv: https://arxiv.org/abs/1908.10059 · HTML: https://mlsanity.com/paper/1908.10059/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Aug 2019.

## Built on by (most cited first, 21 of 21)

- [A Survey of Mix-based Data Augmentation: Taxonomy, Methods, Applications, and Explainability](https://mlsanity.com/paper/2212.10888/) (2022)
- [A Survey on Mixup Augmentations and Beyond](https://mlsanity.com/paper/2409.05202/) (2024)
- [TGDM: Target Guided Dynamic Mixup for Cross-Domain Few-Shot Learning](https://mlsanity.com/paper/2210.05392/) (2022)
- [Contrastive Vicinal Space for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2111.13353/) (2021)
- [GraphMAD: Graph Mixup for Data Augmentation using Data-Driven Convex Clustering](https://mlsanity.com/paper/2210.15721/) (2022)
- [AdaAugment: A Tuning-Free and Adaptive Approach to Enhance Data Augmentation](https://mlsanity.com/paper/2405.11467/) (2024)
- [Data Optimization in Deep Learning: A Survey](https://mlsanity.com/paper/2310.16499/) (2023)
- [Evolving Image Compositions for Feature Representation Learning](https://mlsanity.com/paper/2106.09011/) (2021)
- [Robustmix: Improving Robustness by Regularizing the Frequency Bias of Deep Nets](https://mlsanity.com/paper/2304.02847/) (2023)
- [Mixup Domain Adaptations for Dynamic Remaining Useful Life Predictions](https://mlsanity.com/paper/2404.04824/) (2024)
- [Adversarial Mixing Policy for Relaxing Locally Linear Constraints in Mixup](https://mlsanity.com/paper/2109.07177/) (2021)
- [Data augmentation by morphological mixup for solving Raven's Progressive Matrices](https://mlsanity.com/paper/2103.05222/) (2021)
- [Learning Gradient-based Mixup with Extrapolation toward Flatter Minima for Domain Generalization](https://mlsanity.com/paper/2209.14742/) (2022)
- [Analyzing Effects of Mixed Sample Data Augmentation on Model Interpretability](https://mlsanity.com/paper/2303.14608/) (2023)
- [On Automatic Data Augmentation for 3D Point Cloud Classification](https://mlsanity.com/paper/2112.06029/) (2021)
- [G-Mix: A Generalized Mixup Learning Framework Towards Flat Minima](https://mlsanity.com/paper/2308.03236/) (2023)
- [Feature Expansion and enhanced Compression for Class Incremental Learning](https://mlsanity.com/paper/2405.08038/) (2024)
- [Enlightenment Period Improving DNN Performance](https://mlsanity.com/paper/2504.01737/) (2025)
- [Mixup Helps Understanding Multimodal Video Better](https://mlsanity.com/paper/2510.10986/) (2025)
- [Semi-Supervised Learning under General Causal Models](https://mlsanity.com/paper/2510.22567/) (2025)
- [Cross-Domain Few-Shot Learning for Hyperspectral Image Classification Based on Mixup Foundation Model](https://mlsanity.com/paper/2601.22581/) (2026)

## Abstract (arXiv)

MixUp is an effective data augmentation method to regularize deep neural networks via random linear interpolations between pairs of samples and their labels. It plays an important role in model regularization, semi-supervised learning and domain adaption. However, despite its empirical success, its deficiency of randomly mixing samples has poorly been studied. Since deep networks are capable of memorizing the entire dataset, the corrupted samples generated by vanilla MixUp with a badly chosen interpolation policy will degrade the performance of networks. To overcome the underfitting by corrupted samples, inspired by Meta-learning (learning to learn), we propose a novel technique of learning to mixup in this work, namely, MetaMixUp. Unlike the vanilla MixUp that samples interpolation policy from a predefined distribution, this paper introduces a meta-learning based online optimization approach to dynamically learn the interpolation policy in a data-adaptive way. The validation set performance via meta-learning captures the underfitting issue, which provides more information to refine interpolation policy. Furthermore, we adapt our method for pseudo-label based semisupervised learning (SSL) along with a refined pseudo-labeling strategy. In our experiments, our method achieves better performance than vanilla MixUp and its variants under supervised learning configuration. In particular, extensive experiments show that our MetaMixUp adapted SSL greatly outperforms MixUp and many state-of-the-art methods on CIFAR-10 and SVHN benchmarks under SSL configuration.