GraphTune: A Learning-based Graph Generative Model with Tunable Structural Features
This work addresses a gap in graph generation for applications requiring controlled structural properties, but it is incremental as it builds on existing methods like LSTM and CVAE.
The paper tackles the problem of conditional generation of general graphs by proposing GraphTune, a learning-based generative model that allows tuning of global-level structural features, and shows it outperforms conventional models in evaluations on a real graph dataset.
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.