# Neural Network Architecture for Database Augmentation Using Shared Features

arXiv: https://arxiv.org/abs/2302.01374 · HTML: https://mlsanity.com/paper/2302.01374/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 27 references that are in the map.
- First posted on arXiv 2 Feb 2023.

## Builds on (most cited first, 8 of 8)

- [A systematic study of the class imbalance problem in convolutional neural networks](https://mlsanity.com/paper/1710.05381/) (2017)
- [DeepSMOTE: Fusing Deep Learning and SMOTE for Imbalanced Data](https://mlsanity.com/paper/2105.02340/) (2021)
- [Oversampling for Imbalanced Learning Based on K-Means and SMOTE](https://mlsanity.com/paper/1711.00837/) (2017)
- [VIGAN: Missing View Imputation with Generative Adversarial Networks](https://mlsanity.com/paper/1708.06724/) (2017)
- [An overview of mixing augmentation methods and augmentation strategies](https://mlsanity.com/paper/2107.09887/) (2021)
- [CSMOUTE: Combined Synthetic Oversampling and Undersampling Technique for Imbalanced Data Classification](https://mlsanity.com/paper/2004.03409/) (2020)
- [Neural Network Based Undersampling Techniques](https://mlsanity.com/paper/1908.06487/) (2019)
- [Combining datasets to increase the number of samples and improve model fitting](https://mlsanity.com/paper/2210.05165/) (2022)

## Abstract (arXiv)

The popularity of learning from data with machine learning and neural networks has lead to the creation of many new datasets for almost every problem domain. However, even within a single domain, these datasets are often collected with disparate features, sampled from different sub-populations, and recorded at different time points. Even with the plethora of individual datasets, large data science projects can be difficult as it is often not trivial to merge these smaller datasets. Inherent challenges in some domains such as medicine also makes it very difficult to create large single source datasets or multi-source datasets with identical features. Instead of trying to merge these non-matching datasets directly, we propose a neural network architecture that can provide data augmentation using features common between these datasets. Our results show that this style of data augmentation can work for both image and tabular data.