HiGen: Hierarchical Graph Generative Networks

TL;DR

HiGen introduces a hierarchical graph generative network that models the multi-level structure of graphs, enabling scalable and high-quality generation of complex graphs with community structures.

Contribution

It proposes a novel hierarchical, coarse-to-fine graph generation method that captures community structures and cross-edges, improving scalability and graph quality.

Findings

Achieves state-of-the-art performance on benchmark datasets.

Demonstrates scalability to large, complex graphs.

Effectively models hierarchical and community structures.

Abstract

Most real-world graphs exhibit a hierarchical structure, which is often overlooked by existing graph generation methods. To address this limitation, we propose a novel graph generative network that captures the hierarchical nature of graphs and successively generates the graph sub-structures in a coarse-to-fine fashion. At each level of hierarchy, this model generates communities in parallel, followed by the prediction of cross-edges between communities using separate neural networks. This modular approach enables scalable graph generation for large and complex graphs. Moreover, we model the output distribution of edges in the hierarchical graph with a multinomial distribution and derive a recursive factorization for this distribution. This enables us to generate community graphs with integer-valued edge weights in an autoregressive manner. Empirical studies demonstrate the effectiveness and scalability of our proposed generative model, achieving state-ofthe-art performance in terms of graph quality across various benchmark datasets. The code is available at https://github.com/Karami-m/HiGen_main.