# Generative Expansion of Small Datasets: An Expansive Graph Approach

arXiv: https://arxiv.org/abs/2406.17238 · HTML: https://mlsanity.com/paper/2406.17238/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 20 references that are in the map.
- First posted on arXiv 25 Jun 2024.

## Builds on (most cited first, 6 of 6)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [A Neural Algorithm of Artistic Style](https://mlsanity.com/paper/1508.06576/) (2015)
- [DLKoopman: A deep learning software package for Koopman theory](https://mlsanity.com/paper/2211.08992/) (2022)
- [Koopcon: A new approach towards smarter and less complex learning](https://mlsanity.com/paper/2405.13866/) (2024)

## Built on by (most cited first, 2 of 2)

- [ViTCAE: ViT-based Class-conditioned Autoencoder](https://mlsanity.com/paper/2509.16554/) (2025)
- [Robust Explanatory Analysis for Structured Optimization Networks (REASON) in Learning](https://mlsanity.com/paper/2610.19378/) (2026)

## Abstract (arXiv)

Limited data availability in machine learning significantly impacts performance and generalization. Traditional augmentation methods enhance moderately sufficient datasets. GANs struggle with convergence when generating diverse samples. Diffusion models, while effective, have high computational costs. We introduce an Expansive Synthesis model generating large-scale, information-rich datasets from minimal samples. It uses expander graph mappings and feature interpolation to preserve data distribution and feature relationships. The model leverages neural networks' non-linear latent space, captured by a Koopman operator, to create a linear feature space for dataset expansion. An autoencoder with self-attention layers and optimal transport refines distributional consistency. We validate by comparing classifiers trained on generated data to those trained on original datasets. Results show comparable performance, demonstrating the model's potential to augment training data effectively. This work advances data generation, addressing scarcity in machine learning applications.