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

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.

The paper was published in IEEE Transactions on Network Science and Engineering (2023). An earlier and short version of this paper was presented at the 41st IEEE International Conference on Distributed Computing Systems (ICDCS 2021) Poster Track

References in corpus (5)

• Fast unfolding of communities in large networks
• Hierarchical Generation of Molecular Graphs using Structural Motifs
• GraphGen: A Scalable Approach to Domain-agnostic Labeled Graph Generation
• Disentangling Interpretable Generative Parameters of Random and Real-World Graphs
• A Tunable Model for Graph Generation Using LSTM and Conditional VAE

Cited by in corpus (1)

• An Accurate Graph Generative Model with Tunable Features