English

Wasserstein Adversarially Regularized Graph Autoencoder

Machine Learning 2021-11-10 v1

Abstract

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}
}

Comments

8 pages. 2021 NeurIPS OTML Workshop

R2 v1 2026-06-24T07:31:51.730Z