Curvature Graph Generative Adversarial Networks

11Citations
Citations of this article
19Readers
Mendeley users who have this article in their library.
Get full text

Abstract

Generative adversarial network (GAN) is widely used for generalized and robust learning on graph data. However, for non-Euclidean graph data, the existing GAN-based graph representation methods generate negative samples by random walk or traverse in discrete space, leading to the information loss of topological properties (e.g. hierarchy and circularity). Moreover, due to the topological heterogeneity (i.e., different densities across the graph structure) of graph data, they suffer from serious topological distortion problems. In this paper, we proposed a novel Curvature Graph Generative Adversarial Networks method, named CurvGAN, which is the first GAN-based graph representation method in the Riemannian geometric manifold. To better preserve the topological properties, we approximate the discrete structure as a continuous Riemannian geometric manifold and generate negative samples efficiently from the wrapped normal distribution. To deal with the topological heterogeneity, we leverage the Ricci curvature for local structures with different topological properties, obtaining to low-distortion representations. Extensive experiments show that CurvGAN consistently and significantly outperforms the state-of-the-art methods across multiple tasks and shows superior robustness and generalization.

Cite

CITATION STYLE

APA

Li, J., Fu, X., Sun, Q., Ji, C., Tan, J., Wu, J., & Peng, H. (2022). Curvature Graph Generative Adversarial Networks. In WWW 2022 - Proceedings of the ACM Web Conference 2022 (pp. 1528–1537). Association for Computing Machinery, Inc. https://doi.org/10.1145/3485447.3512199

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free