GraphTune: A Learning-based Graph Generative Model with Tunable Structural Features

TL;DR

GraphTune is a novel learning-based graph generative model that enables explicit tuning of global structural features in generated graphs, improving control over graph properties compared to existing models.

Contribution

The paper introduces GraphTune, a new model that allows conditional generation of graphs with tunable global structural features using LSTM and CVAE.

Findings

GraphTune effectively tunes global structural features.

It outperforms conventional models in feature control.

The model demonstrates versatility on real graph datasets.

Abstract

Generative models for graphs have been actively studied for decades, and they have a wide range of applications. Recently, learning-based graph generation that reproduces real-world graphs has been attracting the attention of many researchers. Although several generative models that utilize modern machine learning technologies have been proposed, conditional generation of general graphs has been less explored in the field. In this paper, we propose a generative model that allows us to tune the value of a global-level structural feature as a condition. Our model, called GraphTune, makes it possible to tune the value of any structural feature of generated graphs using Long Short Term Memory (LSTM) and a Conditional Variational AutoEncoder (CVAE). We performed comparative evaluations of GraphTune and conventional models on a real graph dataset. The evaluations show that GraphTune makes it possible to more clearly tune the value of a global-level structural feature better than conventional models.