This paper introduces Wasserstein Adversarially Regularized Graph Autoencoder (WARGA), an implicit generative algorithm that directly regularizes the latent distribution of node embedding to a target distribution via the Wasserstein metric. The proposed method has been validated in tasks of link prediction and node clustering on real-world graphs, in which WARGA generally outperforms state-of-the-art models based on Kullback-Leibler (KL) divergence and typical adversarial framework.
Cite
@article{arxiv.2111.04981,
title = {Wasserstein Adversarially Regularized Graph Autoencoder},
author = {Huidong Liang and Junbin Gao},
journal= {arXiv preprint arXiv:2111.04981},
year = {2021}
}