# Realistic Synthetic Social Networks with Graph Neural Networks

arXiv: https://arxiv.org/abs/2212.07843 · HTML: https://mlsanity.com/paper/2212.07843/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 52 references that are in the map.
- First posted on arXiv 15 Dec 2022.

## Builds on (most cited first, 16 of 16)

- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [MolGAN: An implicit generative model for small molecular graphs](https://mlsanity.com/paper/1805.11973/) (2018)
- [Deep Learning on Graphs: A Survey](https://mlsanity.com/paper/1812.04202/) (2018)
- [GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoders](https://mlsanity.com/paper/1802.03480/) (2018)
- [Efficient Graph Generation with Graph Recurrent Attention Networks](https://mlsanity.com/paper/1910.00760/) (2019)
- [NetGAN: Generating Graphs via Random Walks](https://mlsanity.com/paper/1803.00816/) (2018)
- [GraphGAN: Graph Representation Learning with Generative Adversarial Nets](https://mlsanity.com/paper/1711.08267/) (2017)
- [A Systematic Survey on Deep Generative Models for Graph Generation](https://mlsanity.com/paper/2007.06686/) (2020)
- [Community Interaction and Conflict on the Web](https://mlsanity.com/paper/1803.03697/) (2018)
- [A Survey on Deep Graph Generation: Methods and Applications](https://mlsanity.com/paper/2203.06714/) (2022)
- [GEMSEC: Graph Embedding with Self Clustering](https://mlsanity.com/paper/1802.03997/) (2018)
- [Little Ball of Fur: A Python Library for Graph Sampling](https://mlsanity.com/paper/2006.04311/) (2020)
- [De-anonymizing Social Networks with Overlapping Community Structure](https://mlsanity.com/paper/1712.04282/) (2017)
- [A Community-aware Network Growth Model for Synthetic Social Network Generation](https://mlsanity.com/paper/1901.03629/) (2019)
- [MEDICI: A simple to use synthetic social network data generator](https://mlsanity.com/paper/2101.01956/) (2021)
- [Political Communities on Twitter: Case Study of the 2022 French Presidential Election](https://mlsanity.com/paper/2204.07436/) (2022)

## Built on by (most cited first, 5 of 5)

- [Size Matters: Large Graph Generation with HiGGs](https://mlsanity.com/paper/2306.11412/) (2023)
- [Tensor-Fused Multi-View Graph Contrastive Learning](https://mlsanity.com/paper/2410.15247/) (2024)
- [Addressing the Impact of Localized Training Data in Graph Neural Networks](https://mlsanity.com/paper/2307.12689/) (2023)
- [Toward a Unified Geometry Understanding: Riemannian Diffusion Framework for Graph Generation and Prediction](https://mlsanity.com/paper/2510.04522/) (2025)
- [Pruning and Quantization Impact on Graph Neural Networks](https://mlsanity.com/paper/2510.22058/) (2025)

## Abstract (arXiv)

Social network analysis faces profound difficulties in sharing data between researchers due to privacy and security concerns. A potential remedy to this issue are synthetic networks, that closely resemble their real counterparts, but can be freely distributed. generating synthetic networks requires the creation of network topologies that, in application, function as realistically as possible. Widely applied models are currently rule-based and can struggle to reproduce structural dynamics. Lead by recent developments in Graph Neural Network (GNN) models for network generation we evaluate the potential of GNNs for synthetic social networks. Our GNN use is specifically within a reasonable use-case and includes empirical evaluation using Maximum Mean Discrepancy (MMD). We include social network specific measurements which allow evaluation of how realistically synthetic networks behave in typical social network analysis applications. We find that the Gated Recurrent Attention Network (GRAN) extends well to social networks, and in comparison to a benchmark popular rule-based generation Recursive-MATrix (R-MAT) method, is better able to replicate realistic structural dynamics. We find that GRAN is more computationally costly than R-MAT, but is not excessively costly to employ, so would be effective for researchers seeking to create datasets of synthetic social networks.