GraphCGAN: Convolutional Graph Neural Network with Generative Adversarial Networks

Sheng Zhang, Rui Song, Wenbin Lu

Abstract:

Graph convolutional networks (GCN) achieved superior performances in graph-based semi-supervised learning (SSL) tasks.
Generative adversarial networks (GAN) also show the ability to increase the performance in SSL.
However, there is still no good way to combine the GAN and GCN in graph-based SSL tasks.
In this work, we present GraphCGAN, a novel framework to incorporate adversarial learning with convolution-based graph neural networks, to operate on graph-structured data.
In GraphCGAN, we show that generator can generate topology structure and features of fake nodes jointly and boost the performance of convolution-based graph neural networks classifier.
In a number of experiments on benchmark datasets, we show that the proposed GraphCGAN outperforms the baseline methods by a significant margin.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=ULthAsOkMs