Heterogeneous Graph Generation: A Hierarchical Approach using Node Feature Pooling

TL;DR

This paper introduces a hierarchical method for generating realistic heterogeneous graphs by modeling node types and features separately, using a diffusion model, encoder, sampler, and feature pool, validated on IMDB and DBLP datasets.

Contribution

A novel two-phase hierarchical framework for heterogeneous graph generation that effectively captures complex node type and feature distributions.

Findings

The method outperforms existing approaches on benchmark datasets.

Component analysis shows the importance of each architectural element.

Generated graphs closely resemble real-world data in structure and diversity.

Abstract

Heterogeneous graphs are present in various domains, such as social networks, recommendation systems, and biological networks. Unlike homogeneous graphs, heterogeneous graphs consist of multiple types of nodes and edges, each representing different entities and relationships. Generating realistic heterogeneous graphs that capture the complex interactions among diverse entities is a difficult task due to several reasons. The generator has to model both the node type distribution along with the feature distribution for each node type. In this paper, we look into solving challenges in heterogeneous graph generation, by employing a two phase hierarchical structure, wherein the first phase creates a skeleton graph with node types using a prior diffusion based model and in the second phase, we use an encoder and a sampler structure as generator to assign node type specific features to the nodes. A discriminator is used to guide training of the generator and feature vectors are sampled from a node feature pool. We conduct extensive experiments with subsets of IMDB and DBLP datasets to show the effectiveness of our method and also the need for various architecture components.