Graph generator creates customizable synthetic networks for gnn testing
SynCo: Synthetic Community-Aware Attributed Graph Generator for Graph Neural Network Benchmarking
Social and Information NetworksMachine Learning
Summary
Identifying community groups in networks like social graphs is hard because real-world data with clear group labels is rare. The authors created SynCo, a tool that makes fake graphs with customizable communities and node connections. This helps test and improve graph neural networks by providing reliable data that mimics real patterns without relying on limited existing datasets. SynCo can generate very large graphs, supporting research at a scale that was difficult before.
What this means in practice
- •For machine learning engineers: Generate synthetic graph datasets with controlled community and degree properties for developing and benchmarking graph neural network models.
- •For network analysts: Create large-scale synthetic networks to simulate and study community structures without relying on scarce real-world labeled data.
Authors
Guilherme Henrique Messias, Mariana Caravanti de Souza, Sylvia Iasulaitis, Alan Demétrius Baria Valejo
Abstract
Graph Neural Networks (GNNs) are powerful models for handling attributed graphs in tasks such as classification, link prediction, and community detection, as they enable the aggregation of information from both structural and semantic sources. However, progress in community detection is hindered by the lack of high-quality datasets, since ground-truth community labels are often unavailable and most algorithms proposed in recent literature rely on the same benchmark datasets for model training and evaluation. To address this issue, attributed random graph generators are commonly employed to create synthetic graphs for assessing the strengths and limitations of GNN-based models. Nevertheless, most existing generators rely heavily on power-law degree distributions, despite recent evidence indicating that scale-free networks are rare, particularly in social network contexts. Moreover, state-of-the-art attributed graph generators provide limited flexibility, as they do not allow users to construct communities with varying densities, degree distributions, and sub-community structures. To overcome these limitations, we introduce the Synthetic Community-Aware Attributed Graph Generator (SynCo), a graph generation algorithm that allows users to control the node degree distribution and sub-community structure. We evaluate SynCo across three different tasks: graph mimicking, hyperparameter evaluation, and node clustering tuning. The results show that our model outperforms state-of-the-art approaches in synthetic graph generation and data augmentation, while preserving the original distributions of duplicated and augmented datasets, as confirmed by statistical tests well know in literature. We also demonstrate the ability of SynCo to generate nodes in large scale, up to 2.1 million nodes.