# Data Augmentation in Graph Neural Networks: The Role of Generated Synthetic Graphs

arXiv: https://arxiv.org/abs/2407.14765 · HTML: https://mlsanity.com/paper/2407.14765/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 20 references that are in the map.
- First posted on arXiv 20 Jul 2024.

## Builds on (most cited first, 15 of 15)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models](https://mlsanity.com/paper/1802.08773/) (2018)
- [Efficient Graph Generation with Graph Recurrent Attention Networks](https://mlsanity.com/paper/1910.00760/) (2019)
- [AugGPT: Leveraging ChatGPT for Text Data Augmentation](https://mlsanity.com/paper/2302.13007/) (2023)
- [Leaving Reality to Imagination: Robust Classification via Generated Datasets](https://mlsanity.com/paper/2302.02503/) (2023)
- [This dataset does not exist: training models from generated images](https://mlsanity.com/paper/1911.02888/) (2019)
- [MoCL: Data-driven Molecular Fingerprint via Knowledge-aware Contrastive Learning from Molecular Graph](https://mlsanity.com/paper/2106.04509/) (2021)
- [Edge Contraction Pooling for Graph Neural Networks](https://mlsanity.com/paper/1905.10990/) (2019)
- [Spectral Augmentation for Self-Supervised Learning on Graphs](https://mlsanity.com/paper/2210.00643/) (2022)
- [Unleashing the Power of Graph Data Augmentation on Covariate Distribution Shift](https://mlsanity.com/paper/2211.02843/) (2022)
- [Deep Representation Learning for Social Network Analysis](https://mlsanity.com/paper/1904.08547/) (2019)
- [Data Augmentation for Graph Convolutional Network on Semi-Supervised Classification](https://mlsanity.com/paper/2106.08848/) (2021)
- [GRAN is superior to GraphRNN: node orderings, kernel- and graph embeddings-based metrics for graph generators](https://mlsanity.com/paper/2307.06709/) (2023)

## Built on by (most cited first, 1 of 1)

- [GraphK: Variable-Size Graph Generation with Efficient Edge Construction](https://mlsanity.com/paper/2608.18777/) (2026)

## Abstract (arXiv)

Graphs are crucial for representing interrelated data and aiding predictive modeling by capturing complex relationships. Achieving high-quality graph representation is important for identifying linked patterns, leading to improvements in Graph Neural Networks (GNNs) to better capture data structures. However, challenges such as data scarcity, high collection costs, and ethical concerns limit progress. As a result, generative models and data augmentation have become more and more popular. This study explores using generated graphs for data augmentation, comparing the performance of combining generated graphs with real graphs, and examining the effect of different quantities of generated graphs on graph classification tasks. The experiments show that balancing scalability and quality requires different generators based on graph size. Our results introduce a new approach to graph data augmentation, ensuring consistent labels and enhancing classification performance.