Labeled Graph Generative Adversarial Networks

TL;DR

This paper introduces LGGAN, a novel generative adversarial network designed to produce labeled graph data, demonstrating superior quality and structural fidelity across various graph datasets and downstream classification tasks.

Contribution

LGGAN is the first to effectively generate labeled graph-structured data with high diversity and structural accuracy, outperforming existing methods.

Findings

LGGAN generates diverse, high-quality labeled graphs.

Generated graphs match the structural characteristics of training data.

LGGAN improves downstream graph classification performance.

Abstract

As a new approach to train generative models, \emph{generative adversarial networks} (GANs) have achieved considerable success in image generation. This framework has also recently been applied to data with graph structures. We propose labeled-graph generative adversarial networks (LGGAN) to train deep generative models for graph-structured data with node labels. We test the approach on various types of graph datasets, such as collections of citation networks and protein graphs. Experiment results show that our model can generate diverse labeled graphs that match the structural characteristics of the training data and outperforms all alternative approaches in quality and generality. To further evaluate the quality of the generated graphs, we use them on a downstream task of graph classification, and the results show that LGGAN can faithfully capture the important aspects of the graph structure.