# Augment on Manifold: Mixup Regularization with UMAP

arXiv: https://arxiv.org/abs/2312.13141 · HTML: https://mlsanity.com/paper/2312.13141/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 21 references that are in the map.
- First posted on arXiv 20 Dec 2023.

## Builds on (most cited first, 11 of 11)

- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [MixUp as Locally Linear Out-Of-Manifold Regularization](https://mlsanity.com/paper/1809.02499/) (2018)
- [Remix: Rebalanced Mixup](https://mlsanity.com/paper/2007.03943/) (2020)
- [Parametric UMAP embeddings for representation and semi-supervised learning](https://mlsanity.com/paper/2009.12981/) (2020)
- [C-Mixup: Improving Generalization in Regression](https://mlsanity.com/paper/2210.05775/) (2022)
- [Preventing Manifold Intrusion with Locality: Local Mixup](https://mlsanity.com/paper/2201.04368/) (2022)
- [Evaluating data augmentation for financial time series classification](https://mlsanity.com/paper/2010.15111/) (2020)
- [MixupE: Understanding and Improving Mixup from Directional Derivative Perspective](https://mlsanity.com/paper/2212.13381/) (2022)
- [Why have a Unified Predictive Uncertainty? Disentangling it using Deep Split Ensembles](https://mlsanity.com/paper/2009.12406/) (2020)
- [Deep Gaussian Mixture Ensembles](https://mlsanity.com/paper/2306.07235/) (2023)

## Built on by (most cited first, 3 of 3)

- [A Survey on Mixup Augmentations and Beyond](https://mlsanity.com/paper/2409.05202/) (2024)
- [Mixup Regularization: A Probabilistic Perspective](https://mlsanity.com/paper/2502.13825/) (2025)
- [Controlled Paraphrase Geometry in Sentence Embedding Space: Local Manifold Modeling and Latent Probing](https://mlsanity.com/paper/2605.01073/) (2026)

## Abstract (arXiv)

Data augmentation techniques play an important role in enhancing the performance of deep learning models. Despite their proven benefits in computer vision tasks, their application in the other domains remains limited. This paper proposes a Mixup regularization scheme, referred to as UMAP Mixup, designed for ``on-manifold" automated data augmentation for deep learning predictive models. The proposed approach ensures that the Mixup operations result in synthesized samples that lie on the data manifold of the features and labels by utilizing a dimensionality reduction technique known as uniform manifold approximation and projection. Evaluations across diverse regression tasks show that UMAP Mixup is competitive with or outperforms other Mixup variants, show promise for its potential as an effective tool for enhancing the generalization performance of deep learning models.