Wasserstein Adversarially Regularized Graph Autoencoder

• Published in: Neurocomputing (Amsterdam) Vol. 541; p. 126235
• Main Authors: Liang, Huidong, Gao, Junbin
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 07.07.2023
• Subjects: Adversarial training; Graph neural networks; Variational autoencoder; Wasserstein distance; Variational autoencoder; Wasserstein distance; Graph neural networks; Adversarial training; 00–01; 99–00
• ISSN: 0925-2312; 1872-8286
• DOI: 10.1016/j.neucom.2023.126235

•Application of Wasserstein distance under graph settings.•Using Wasserstein distance for node embedding regularization.•Applying weight clipping and gradient penalty approaches for Lipschitz continuity.•Comparison of regularization against KL divergence and adversarial methods.•Detailed experiment on link prediction, node clustering and embedding visualization. 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. To ensure the Lipschitz continuity, we propose two approaches: WARGA-WC that uses weight clipping method and WARGA-GP that uses gradient penalty method. The proposed models have been validated by link prediction and node clustering on real-world graphs with visualizations of node embeddings, in which WARGA generally outperforms other state-of-the-art models based on Kullback–Leibler (KL) divergence and typical adversarial framework.