arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.01604cs.LGcs.SI
收藏

曲率图生成对抗网络

Curvature Graph Generative Adversarial Networks

Beihang University(北京航空航天大学);Macquarie University(麦考瑞大学)

Jianxin Li, Xingcheng Fu, Qingyun Sun, Cheng Ji, Jiajun Tan, Jia Wu, Hao Peng

摘要:

生成对抗网络(GAN)被广泛用于图数据的广义和鲁棒学习。然而,对于非欧图数据,现有的基于GAN的图表示方法通过离散空间中的随机行走或遍历来生成负样本,导致拓扑属性(例如层次和圆度)的信息丢失。此外,由于拓扑异构性(即,图数据的不同密度),它们遭受严重的拓扑失真问题。在本文中,我们提出了一种新的曲率图生成对抗网络方法,命名为\textbf{\modelname},这是黎曼几何流形中第一个基于GAN的图表示方法。为了更好地保持拓扑性质,我们近似的离散结构作为一个连续的黎曼几何流形和生成负样本有效地从包裹的正态分布。为了处理拓扑异构性,我们利用Ricci曲率的局部结构具有不同的拓扑性质,获得低失真的表示。大量的实验表明,CurvGAN在多个任务中的表现始终显著优于最先进的方法,并显示出卓越的鲁棒性和泛化能力。

英文摘要:

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 \textbf{\modelname}, 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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑