Efficient Synthetic Network Generation via Latent Embedding Reconstruction

Network data are ubiquitous across the social sciences, biology, and information systems. Generating realistic synthetic network data has broad applications from network simulation to scientific discovery. However, many existing black-box approaches for network generation tend to overfit observed data while overlooking characteristic network structure, and incur substantial computational overhead at scale. These practical challenges call for synthetic network generation methods that are both efficient and capable of capturing structural properties of networks. In this paper, we introduce Synthetic Network Generation via Latent Embedding Reconstruction (SyNGLER), a general and efficient framework for synthetic network generation that builds on latent space network models. Given an observed network, SyNGLER first learns low-dimensional latent node embeddings via a latent space network model and then reconstructs the latent space by building a distribution-free generator over these embeddings. For generation, SyNGLER first samples (or resamples) node embeddings from the generator in the latent space and then produces synthetic networks using the latent space network model. Through the latent space framework, SyNGLER preserves unique characteristics in networks such as sparsity and node degree heterogeneity, while allowing for efficient training with lower computational cost than many existing deep architectures. We provide theoretical guarantees by developing consistency results on the distance between the true and synthetic edge distributions. Empirical studies further demonstrate the effectiveness of SyNGLER, which efficiently produces networks that better preserve key network characteristics such as network moments and degree distributions compared with existing approaches. Code is available at https://github.com/FeifanJiang/syngler.

Many real-world datasets can often be modeled as networks. Generating synthetic networks appears to be an increasingly important task. However, many existing methods are slow and do not always preserve important network patterns, especially given the scale of modern datasets. To solve this problem, we propose SyNGLER, a simple framework for synthetic network generation. SyNGLER first learns a latent representation for each node, describing where the node sits in a latent space and how connected it tends to be. It then learns how these node representations are distributed and uses them to generate a new network. Because SyNGLER works in a structurally simple latent space, it is significantly more efficient. Experiments show that it can preserve key network structures, such as degree patterns, clustering, and spectral properties, while using less computation compared with modern deep models.