Deep Generation of Heterogeneous Networks

TL;DR

This paper introduces HGEN, a novel framework for generating heterogeneous graphs by modeling local and global distributions, capturing semantic and structural properties, and assembling realistic graphs from generated meta-paths.

Contribution

The paper presents a new hierarchical graph generation framework that jointly models semantic, structural, and global distributions of heterogeneous graphs.

Findings

HGEN effectively generates realistic heterogeneous graphs.

Theoretical analysis confirms pattern preservation.

Experiments demonstrate superior performance on real-world datasets.

Abstract

Heterogeneous graphs are ubiquitous data structures that can inherently capture multi-type and multi-modal interactions between objects. In recent years, research on encoding heterogeneous graph into latent representations have enjoyed a rapid increase. However, its reverse process, namely how to construct heterogeneous graphs from underlying representations and distributions have not been well explored due to several challenges in 1) modeling the local heterogeneous semantic distribution; 2) preserving the graph-structured distributions over the local semantics; and 3) characterizing the global heterogeneous graph distributions. To address these challenges, we propose a novel framework for heterogeneous graph generation (HGEN) that jointly captures the semantic, structural, and global distributions of heterogeneous graphs. Specifically, we propose a heterogeneous walk generator that hierarchically generates meta-paths and their path instances. In addition, a novel heterogeneous graph assembler is developed that can sample and combine the generated meta-path instances (e.g., walks) into heterogeneous graphs in a stratified manner. Theoretical analysis on the preservation of heterogeneous graph patterns by the proposed generation process has been performed. Extensive experiments on multiple real-world and synthetic heterogeneous graph datasets demonstrate the effectiveness of the proposed HGEN in generating realistic heterogeneous graphs.