Neural Graph Generator: Feature-Conditioned Graph Generation using Latent Diffusion Models

TL;DR

This paper introduces Neural Graph Generator, a novel method using conditioned latent diffusion models to generate graphs with specific properties, improving control and versatility over existing approaches.

Contribution

The paper presents NGG, a new graph generation approach combining variational autoencoders and diffusion in latent space, enabling property-controlled and diverse graph synthesis.

Findings

NGG effectively models complex graph patterns

NGG can generate graphs with desired properties

NGG generalizes well to unseen graphs

Abstract

Graph generation has emerged as a crucial task in machine learning, with significant challenges in generating graphs that accurately reflect specific properties. Existing methods often fall short in efficiently addressing this need as they struggle with the high-dimensional complexity and varied nature of graph properties. In this paper, we introduce the Neural Graph Generator (NGG), a novel approach which utilizes conditioned latent diffusion models for graph generation. NGG demonstrates a remarkable capacity to model complex graph patterns, offering control over the graph generation process. NGG employs a variational graph autoencoder for graph compression and a diffusion process in the latent vector space, guided by vectors summarizing graph statistics. We demonstrate NGG's versatility across various graph generation tasks, showing its capability to capture desired graph properties and generalize to unseen graphs. We also compare our generator to the graph generation capabilities of different LLMs. This work signifies a shift in graph generation methodologies, offering a more practical and efficient solution for generating diverse graphs with specific characteristics.